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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    prominent names and locations associated with various events and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uador
    -0.62
     âĢº
    -0.59
     <<
    -0.58
    hematically
    -0.56
    rious
    -0.53
    orse
    -0.52
    Pokemon
    -0.52
    ãĥ£
    -0.50
     php
    -0.50
    bitcoin
    -0.49
    POSITIVE LOGITS
     himself
    0.76
     herself
    0.68
     itself
    0.64
     fame
    0.63
     Sr
    0.60
    ledged
    0.57
     confid
    0.55
     Leilan
    0.54
     respectively
    0.53
     headquarters
    0.52
    Act Density 0.814%

    No Known Activations