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

    Neuronpedia

    INDEX
    Explanations

    phrases related to being offended or causing offense

    oai_token-act-pair · gpt-3.5-turbo

    references to being offended or causing offense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issue
    -0.74
     liner
    -0.72
    runner
    -0.71
    tom
    -0.69
    aver
    -0.69
    negie
    -0.68
    hart
    -0.66
    nosis
    -0.66
    ynthesis
    -0.65
    gravity
    -0.65
    POSITIVE LOGITS
     offended
    0.97
     offend
    0.94
     insulted
    0.84
     indecent
    0.80
    Sax
    0.75
     sexist
    0.74
     Yiannopoulos
    0.73
    ingly
    0.72
     bystanders
    0.72
     offending
    0.71
    Act Density 0.018%

    No Known Activations