Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    questions that ask for truthfulness or correctness regarding options or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.89
     Jefus
    -0.83
     Reſ
    -0.82
    AndEndTag
    -0.82
     Juneau
    -0.81
     faſt
    -0.80
     protoimpl
    -0.79
     himſelf
    -0.79
     poffible
    -0.77
     ſeveral
    -0.76
    POSITIVE LOGITS
     A
    0.51
     primary
    0.51
     وتسجيلات
    0.51
    <eos>
    0.48
     Is
    0.47
     Gemeinde
    0.46
    ↵↵
    0.46
     may
    0.45
     T
    0.44
    fortawesome
    0.44
    Act Density 0.341%

    No Known Activations