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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantity or listings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.84
    rungsseite
    -0.84
     itſelf
    -0.73
     myſelf
    -0.67
    ########.
    -0.65
    ंदीखरीदारी
    -0.63
     Theſe
    -0.63
    ApiModelProperty
    -0.61
    ſelf
    -0.61
     houſe
    -0.60
    POSITIVE LOGITS
     שוליים
    0.60
    FOR
    0.59
     For
    0.58
     FOR
    0.57
    CloseOperation
    0.56
    For
    0.52
    for
    0.51
    HomeAsUpEnabled
    0.48
     Forster
    0.48
    nargs
    0.48
    Act Density 0.319%

    No Known Activations