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

    Neuronpedia

    INDEX
    Explanations

    words related to conditions or requirements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to conditions or states that precede or express uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.86
    lift
    -0.80
    loo
    -0.73
    bill
    -0.72
    owship
    -0.70
     fronts
    -0.70
    æѦ
    -0.70
    ictionary
    -0.68
     Archdemon
    -0.67
    ãĥ´
    -0.67
    POSITIVE LOGITS
    ocious
    1.17
    ognitive
    0.95
    ursor
    0.94
    ordial
    0.90
    ursed
    0.88
     prec
    0.87
    aching
    0.87
    urs
    0.86
    autions
    0.85
    urity
    0.83
    Act Density 0.026%

    No Known Activations