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

    Neuronpedia

    INDEX
    Explanations

    the name "Gab" at varying activation strengths

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions or references to the name "Gab."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tenance
    -0.82
    IDER
    -0.73
    PATH
    -0.71
    OCK
    -0.71
    ctive
    -0.68
    chnology
    -0.67
    UME
    -0.66
    IGHTS
    -0.65
    soDeliveryDate
    -0.63
    HEAD
    -0.62
    POSITIVE LOGITS
     Gab
    1.06
    riel
    1.03
    onis
    0.92
    ran
    0.92
    raham
    0.85
    ilib
    0.84
    lock
    0.83
    rod
    0.82
    oise
    0.80
    rets
    0.80
    Act Density 0.007%

    No Known Activations