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

    Neuronpedia

    INDEX
    Explanations

    foreign words or proper nouns containing specific characters 'Äį'

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ü
    -0.71
    Interstitial
    -0.69
    AMI
    -0.67
    GBT
    -0.67
    pert
    -0.67
     fortun
    -0.66
    essage
    -0.65
     Azerbai
    -0.64
    comb
    -0.63
    istically
    -0.62
    POSITIVE LOGITS
    ijn
    0.96
    keye
    0.83
    rador
    0.79
    artney
    0.79
    sie
    0.77
    rium
    0.77
    hess
    0.76
    yr
    0.74
    keyes
    0.73
    ovo
    0.72
    Act Density 0.018%

    No Known Activations