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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases indicating causality

    oai_token-act-pair · gpt-3.5-turbo

    verbs that indicate causation or lead to consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    luaj
    -0.75
    quart
    -0.63
    kus
    -0.60
    kt
    -0.59
    pmwiki
    -0.58
     supposed
    -0.58
    Cas
    -0.57
    yd
    -0.57
    phe
    -0.56
     Bastard
    -0.53
    POSITIVE LOGITS
    geries
    0.90
    enance
    0.81
     someday
    0.72
    igate
    0.72
    gery
    0.71
    ificantly
    0.69
    glers
    0.68
    rued
    0.68
    ample
    0.67
     significantly
    0.66
    Act Density 0.265%

    No Known Activations