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

    Neuronpedia

    INDEX
    Explanations

    words related to censorship

    oai_token-act-pair · gpt-3.5-turbo

    terms related to censorship and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    verty
    -0.77
    ndra
    -0.77
     Mead
    -0.75
    ptoms
    -0.74
    ilater
    -0.73
    amac
    -0.73
     Dew
    -0.69
    tell
    -0.67
    rious
    -0.66
    swick
    -0.66
    POSITIVE LOGITS
     censorship
    1.07
     cens
    0.98
     censor
    0.96
     censored
    0.93
     suppressing
    0.78
    zers
    0.72
     blackout
    0.70
     suppression
    0.70
    ourgeois
    0.68
     prohibited
    0.66
    Act Density 0.048%

    No Known Activations