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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating certainty or personal knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ymes
    -0.17
    ainter
    -0.16
    afs
    -0.15
    ahi
    -0.15
    ans
    -0.15
    abor
    -0.15
    alls
    -0.14
    iani
    -0.14
    ayo
    -0.14
     ready
    -0.13
    POSITIVE LOGITS
    edik
    0.17
    snake
    0.15
    ÃľM
    0.14
    /Area
    0.14
    _TP
    0.14
    ozem
    0.14
     hc
    0.14
    arger
    0.13
    _TypeInfo
    0.13
    alars
    0.13
    Act Density 0.006%

    No Known Activations