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

    Neuronpedia

    INDEX
    Explanations

    words related to acrimony or contentiousness

    oai_token-act-pair · gpt-3.5-turbo

    words associated with various forms of criticism or judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dakota
    -0.68
    Preview
    -0.64
    orks
    -0.62
     Hendricks
    -0.57
     Sweden
    -0.56
     Sisters
    -0.55
     Wolves
    -0.54
     Ark
    -0.54
     Girls
    -0.53
    profits
    -0.53
    POSITIVE LOGITS
    erb
    0.90
    yll
    0.89
    ulative
    0.87
    iously
    0.83
    hemer
    0.82
    itatively
    0.81
    iotic
    0.80
    uitous
    0.80
    vity
    0.77
    aution
    0.76
    Act Density 0.140%

    No Known Activations