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

    Neuronpedia

    INDEX
    Explanations

    mentions of appearance or visual resemblance

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe appearance or perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arius
    -0.76
    ufact
    -0.72
    ItemTracker
    -0.65
     Variant
    -0.64
     railing
    -0.63
    olars
    -0.63
    gnu
    -0.62
     toget
    -0.59
    NEWS
    -0.58
    riad
    -0.58
    POSITIVE LOGITS
    vind
    0.76
    lier
    0.73
     smarter
    0.70
     stronger
    0.68
     louder
    0.67
     invincible
    0.65
    operative
    0.64
    uate
    0.64
    ingly
    0.62
    ="#
    0.61
    Act Density 0.081%

    No Known Activations