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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and their relationships in complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PagerAdapter
    -0.72
    usza
    -0.72
     covered
    -0.70
    schild
    -0.68
     Rie
    -0.67
    geable
    -0.66
    transQ
    -0.66
    Autoritní
    -0.65
    colage
    -0.65
    mannian
    -0.63
    POSITIVE LOGITS
     to
    0.83
     بيها
    0.78
     take
    0.74
     help
    0.73
     putea
    0.71
     prove
    0.69
     create
    0.68
     Pennington
    0.68
     intervene
    0.67
     connect
    0.67
    Act Density 0.408%

    No Known Activations