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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating future actions or intentions

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating possibility, obligation, and negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Joy
    -0.80
    csv
    -0.68
    itures
    -0.67
    isters
    -0.65
    itor
    -0.64
    SourceFile
    -0.64
     Cruiser
    -0.64
    aed
    -0.63
    Vs
    -0.63
     Doodle
    -0.61
    POSITIVE LOGITS
     alike
    0.81
    WHERE
    0.73
     depending
    0.68
    SPONSORED
    0.67
     dictated
    0.59
     reproduce
    0.59
     differ
    0.57
     thereafter
    0.57
    rely
    0.57
     BE
    0.56
    Act Density 0.176%

    No Known Activations