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

    Neuronpedia

    INDEX
    Explanations

    words related to causing offense or being offended

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to feelings of offense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gravity
    -0.77
    issue
    -0.73
    rocket
    -0.72
     liner
    -0.71
    tom
    -0.71
    runner
    -0.70
    nosis
    -0.66
    ports
    -0.66
    pring
    -0.66
    hare
    -0.65
    POSITIVE LOGITS
     offend
    0.98
     offended
    0.93
     insulted
    0.80
     Yiannopoulos
    0.79
     indecent
    0.78
     bystanders
    0.76
    netflix
    0.71
     sensibilities
    0.70
    ĸļ
    0.69
     Cartoon
    0.69
    Act Density 0.026%

    No Known Activations