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

    Neuronpedia

    INDEX
    Explanations

    imperative verbs related to giving instructions or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    non-verbal tokens or symbols indicating the presence of multiple segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.67
     behav
    -0.65
     helicop
    -0.63
    farious
    -0.59
     challeng
    -0.58
     respons
    -0.58
    xxxx
    -0.57
    existent
    -0.57
    ãĤ©
    -0.56
     Vaugh
    -0.55
    POSITIVE LOGITS
    resa
    0.73
    BSD
    0.63
    Berry
    0.61
    xiety
    0.60
     Released
    0.60
     largeDownload
    0.59
     Expand
    0.57
     Finder
    0.57
     Updated
    0.57
     Grateful
    0.57
    Act Density 0.361%

    No Known Activations