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

    Neuronpedia

    INDEX
    Explanations

    phrases related to causing offense or being offended

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to causing offense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aver
    -0.78
    ynthesis
    -0.77
    ilk
    -0.76
     liner
    -0.69
    Requirements
    -0.67
    aws
    -0.67
    arijuana
    -0.67
    achine
    -0.66
    ynchron
    -0.65
    achev
    -0.64
    POSITIVE LOGITS
     offend
    1.31
     offended
    1.20
     offending
    1.16
     insulted
    1.06
     blasp
    0.92
     insult
    0.87
     indecent
    0.82
    olini
    0.81
    Sax
    0.80
    Û
    0.77
    Act Density 0.012%

    No Known Activations