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

    Neuronpedia

    INDEX
    Explanations

    words related to winning titles or competitions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to competitive events and championships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     solicit
    -0.67
     discl
    -0.63
     scope
    -0.62
     horizon
    -0.62
     hor
    -0.61
     silhou
    -0.61
     hypocr
    -0.60
    yrics
    -0.59
     consultation
    -0.59
     audible
    -0.58
    POSITIVE LOGITS
     outright
    1.13
     convinc
    1.08
     decisively
    1.03
     twice
    0.89
     despite
    0.83
    Ĥİ
    0.83
     effortlessly
    0.80
     again
    0.78
     Offline
    0.77
     AGA
    0.76
    Act Density 0.185%

    No Known Activations