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

    Neuronpedia

    INDEX
    Explanations

    powerful verbs and adjectives related to strength, control, and authority

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.75
     Cosponsors
    -0.63
    Shares
    -0.59
    atures
    -0.59
    illard
    -0.58
    assetsadobe
    -0.55
    é¾įå¥ij士
    -0.55
    margin
    -0.54
    addy
    -0.54
    arel
    -0.53
    POSITIVE LOGITS
     accountable
    1.04
     afloat
    0.91
     obsolete
    0.86
     alive
    0.83
     shine
    0.83
     unatt
    0.77
     safer
    0.76
     closer
    0.75
     unus
    0.74
     flourish
    0.74
    Act Density 5.040%

    No Known Activations