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

    Neuronpedia

    INDEX
    Explanations

    words related to computer programming and technology

    oai_token-act-pair · gpt-3.5-turbo

    past participle verbs that describe completed actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adra
    -0.74
    oteric
    -0.74
    ively
    -0.73
    adan
    -0.71
    matically
    -0.70
    alog
    -0.70
    verson
    -0.69
    istration
    -0.68
    cially
    -0.67
    ql
    -0.67
    POSITIVE LOGITS
     Ones
    1.03
    nesday
    0.88
     Sharing
    0.83
    ragon
    0.81
    paren
    0.80
    ness
    0.76
     Talent
    0.74
     Items
    0.73
     Missing
    0.73
     Expend
    0.72
    Act Density 0.106%

    No Known Activations