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

    Neuronpedia

    INDEX
    Explanations

    references to "something" or unspecified objects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.20
    ikel
    -0.17
    sar
    -0.17
    odb
    -0.17
    اÙĨÙĩ
    -0.16
    ends
    -0.15
    most
    -0.15
    dez
    -0.15
    ses
    -0.15
    edo
    -0.15
    POSITIVE LOGITS
     else
    0.19
    _else
    0.17
    ylim
    0.17
    Else
    0.16
    awks
    0.15
    assen
    0.15
    许
    0.14
    ecial
    0.14
    ething
    0.14
    else
    0.14
    Act Density 0.073%

    No Known Activations