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

    Neuronpedia

    INDEX
    Explanations

    words related to cognitive abilities

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to cognitive abilities and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FORE
    -0.79
    andro
    -0.77
    EGA
    -0.76
    encer
    -0.74
    wives
    -0.74
    ourced
    -0.70
    olicited
    -0.68
    ãĥĺ
    -0.68
     Polo
    -0.68
     Leone
    -0.68
    POSITIVE LOGITS
     disson
    1.41
     enh
    1.06
     faculties
    0.94
     enhancement
    0.91
     impairment
    0.91
     behavioural
    0.89
    ly
    0.83
     hygiene
    0.83
    istically
    0.79
    izing
    0.78
    Act Density 0.019%

    No Known Activations