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

    Neuronpedia

    INDEX
    Explanations

    phrases related to public statements or actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "public" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kson
    -0.81
    llan
    -0.77
    vell
    -0.73
    imoto
    -0.68
    rax
    -0.68
    nesota
    -0.67
    nian
    -0.67
    Film
    -0.67
    ansas
    -0.66
    webkit
    -0.66
    POSITIVE LOGITS
     relations
    1.16
    izing
    1.04
    ised
    0.99
     shaming
    0.98
    ally
    0.95
     outcry
    0.94
    ising
    0.93
     humiliation
    0.93
     servants
    0.90
     domain
    0.89
    Act Density 0.053%

    No Known Activations