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

    Neuronpedia

    INDEX
    Explanations

    words related to wigs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to wigs and hair pieces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Devon
    -0.79
     Sussex
    -0.74
    Franc
    -0.72
    birth
    -0.71
     Serbia
    -0.67
     Palest
    -0.64
    CLASSIFIED
    -0.63
     Toll
    -0.61
     Catalonia
    -0.61
    Charl
    -0.60
    POSITIVE LOGITS
    glers
    1.30
    gered
    1.06
    aws
    1.05
    igs
    1.04
    hetti
    1.02
    ource
    1.02
    ongs
    1.00
    arettes
    0.99
    angs
    0.96
    aret
    0.96
    Act Density 0.006%

    No Known Activations