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

    Neuronpedia

    INDEX
    Explanations

    invisible characters or special tokens within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utin
    -0.16
    umas
    -0.16
    åĩī
    -0.15
     Gos
    -0.14
     Kor
    -0.14
    ाण
    -0.14
     stabil
    -0.14
    fluid
    -0.14
    rol
    -0.14
    icit
    -0.14
    POSITIVE LOGITS
    reau
    0.16
    oyer
    0.15
    .Slf
    0.15
    PermissionsResult
    0.15
    _PORTS
    0.14
    ICC
    0.14
    chwitz
    0.14
    celik
    0.14
    unas
    0.14
    xcc
    0.14
    Act Density 0.001%

    No Known Activations