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

    Neuronpedia

    INDEX
    Explanations

    words related to non-lethal tools and objects

    oai_token-act-pair · gpt-3.5-turbo

    negations and qualifiers related to safety and compliance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     leadership
    -0.84
     negotiations
    -0.84
     entitlement
    -0.82
     professions
    -0.78
     achievements
    -0.76
     keynote
    -0.76
     acknowled
    -0.74
     preferences
    -0.74
     sentiments
    -0.74
     Events
    -0.74
    POSITIVE LOGITS
    mounted
    1.23
    colored
    1.21
    assembled
    1.14
    printed
    1.14
    fitted
    1.12
    painted
    1.11
    usable
    1.09
    worn
    1.09
    shaped
    1.07
    uminum
    1.05
    Act Density 0.242%

    No Known Activations