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

    Neuronpedia

    INDEX
    Explanations

    references to specific portions or segments of text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bondale
    -0.56
     boe
    -0.55
    nowy
    -0.55
    avari
    -0.55
    <?>>
    -0.54
     vœux
    -0.54
    obie
    -0.53
     padrões
    -0.53
     Willen
    -0.53
     Westmoreland
    -0.52
    POSITIVE LOGITS
     portions
    0.88
     portion
    0.83
     parts
    0.80
     segments
    0.76
     sections
    0.76
     part
    0.75
    Portion
    0.73
     Portion
    0.73
     segment
    0.72
    portion
    0.68
    Act Density 0.496%

    No Known Activations