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

    Neuronpedia

    INDEX
    Explanations

    negative terms or insults directed towards individuals

    oai_token-act-pair · gpt-3.5-turbo

    derogatory labels or insults directed at individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    foreseen
    -0.65
    eto
    -0.64
    ubuntu
    -0.62
    strip
    -0.61
    olar
    -0.61
    ispers
    -0.61
    iasm
    -0.61
    uce
    -0.59
     lured
    -0.59
     Remastered
    -0.59
    POSITIVE LOGITS
    SourceFile
    0.71
    Tes
    0.70
     "
    0.70
     necessity
    0.66
     bluff
    0.65
     '
    0.64
     Jem
    0.63
     nuisance
    0.61
    ="#
    0.61
    ãĢİ
    0.60
    Act Density 0.129%

    No Known Activations