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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intention or purpose

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating purpose or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anon
    -0.68
     knots
    -0.63
     Solitaire
    -0.62
     Carbuncle
    -0.61
     Figures
    -0.58
    natureconservancy
    -0.58
     Regions
    -0.56
    chapter
    -0.55
     Transcript
    -0.54
    amac
    -0.53
    POSITIVE LOGITS
     primarily
    0.81
     solely
    0.80
     principally
    0.76
     purely
    0.74
     aimed
    0.73
     Parenthood
    0.73
    wark
    0.72
     exclusively
    0.68
    paren
    0.67
    ysc
    0.67
    Act Density 0.050%

    No Known Activations