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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    íĬ
    -0.16
    ikip
    -0.15
    STA
    -0.15
    ymoon
    -0.15
    аÑĤом
    -0.14
    _WAKE
    -0.14
     voks
    -0.14
    rok
    -0.14
    iggins
    -0.14
    ded
    -0.14
    POSITIVE LOGITS
    ILINE
    0.17
    edia
    0.15
    ews
    0.15
     Quart
    0.14
    mür
    0.14
    quests
    0.14
     Velvet
    0.14
    IDI
    0.14
    igh
    0.14
     Rays
    0.14
    Act Density 0.112%

    No Known Activations