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

    Neuronpedia

    INDEX
    Explanations

    verbs that express actions or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    negations or expressions of inability or impossibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    catentry
    -0.73
    study
    -0.67
     Almighty
    -0.62
    LAB
    -0.58
    LIN
    -0.58
    ithing
    -0.57
    ilst
    -0.57
     Sabbath
    -0.55
     spectrum
    -0.55
     Milton
    -0.54
    POSITIVE LOGITS
     anymore
    1.29
     bothered
    0.93
     ANY
    0.84
    */(
    0.83
     nor
    0.79
     anywhere
    0.79
     Enough
    0.76
     bothering
    0.75
     bother
    0.74
     enough
    0.74
    Act Density 0.388%

    No Known Activations