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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms related to criticism or controversy

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "offensive" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chell
    -0.83
    omed
    -0.72
    perature
    -0.71
    Deal
    -0.70
    ilk
    -0.69
    Export
    -0.68
     Cups
    -0.67
    aret
    -0.67
    obook
    -0.67
     Cind
    -0.66
    POSITIVE LOGITS
    ity
    0.78
    ities
    0.74
     thrust
    0.69
     offensive
    0.67
    thouse
    0.66
     posture
    0.63
     bowel
    0.63
     reb
    0.61
    ments
    0.61
     arte
    0.60
    Act Density 0.022%

    No Known Activations