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

    Neuronpedia

    INDEX
    Explanations

    elements related to discussion or focus in a text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to discussions, subjects, or prominent topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tnc
    -0.82
    CRIP
    -0.74
    earances
    -0.72
    respect
    -0.66
    thood
    -0.66
    each
    -0.64
    abwe
    -0.63
    teness
    -0.62
    hemy
    -0.61
    é»Ĵ
    -0.61
    POSITIVE LOGITS
    liest
    1.50
    iest
    1.29
     equivalent
    1.05
     centerpiece
    0.99
    hest
    0.95
     pinnacle
    0.91
    ultimate
    0.89
     easiest
    0.89
     safest
    0.88
     antidote
    0.86
    Act Density 0.294%

    No Known Activations