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

    Neuronpedia

    INDEX
    Explanations

    suggestions or recommendations made in a document

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express suggestions, recommendations, or advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agos
    -0.71
    TED
    -0.65
    ELD
    -0.65
     Ern
    -0.64
    backer
    -0.63
    Runtime
    -0.62
    ARDS
    -0.62
    IGHTS
    -0.61
    Leod
    -0.59
     Sabha
    -0.59
    POSITIVE LOGITS
    ħĭ
    0.98
    eele
    0.82
     reconsider
    0.80
     nominate
    0.75
    uyomi
    0.72
    yip
    0.72
    ramid
    0.71
     Architects
    0.69
     jurors
    0.69
     bluff
    0.67
    Act Density 0.164%

    No Known Activations