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

    Neuronpedia

    INDEX
    Explanations

    words related to the origin or source of something

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of origin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     helicop
    -0.65
     absentee
    -0.63
    PDATE
    -0.63
    Agg
    -0.62
     Eye
    -0.60
    anyahu
    -0.58
    ĵĺ
    -0.58
    peak
    -0.58
    owl
    -0.57
    orld
    -0.57
    POSITIVE LOGITS
    ator
    1.17
    ators
    1.14
    ates
    1.10
    uating
    0.90
    uation
    0.85
    acy
    0.79
    uated
    0.79
    itious
    0.77
    uates
    0.77
    ories
    0.76
    Act Density 0.026%

    No Known Activations