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

    Neuronpedia

    INDEX
    Explanations

    keywords related to asking or desiring information or solutions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desire or requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wounding
    -0.69
     Solitaire
    -0.65
     Shards
    -0.59
     stride
    -0.59
     Sierra
    -0.57
     slopes
    -0.57
     Ragnar
    -0.57
     Seym
    -0.56
     embod
    -0.56
    cision
    -0.55
    POSITIVE LOGITS
    igslist
    0.83
    reprene
    0.83
    agh
    0.79
    atile
    0.77
    anta
    0.76
    ful
    0.76
    on
    0.75
    ony
    0.75
    onia
    0.73
    only
    0.71
    Act Density 0.067%

    No Known Activations