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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong positive sentiment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong positive sentiment or affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Inquiry
    -0.64
    imester
    -0.63
    å°Ĩ
    -0.62
    Phase
    -0.62
    ufact
    -0.61
    ocument
    -0.61
     Regist
    -0.61
    UME
    -0.61
    UTE
    -0.60
    ailable
    -0.60
    POSITIVE LOGITS
     dearly
    0.75
     hobby
    0.71
     solitude
    0.66
     arts
    0.65
     generosity
    0.65
    animous
    0.65
     spont
    0.64
    otrop
    0.63
    cel
    0.63
     openness
    0.63
    Act Density 0.236%

    No Known Activations