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

    Neuronpedia

    INDEX
    Explanations

    code-related terms and functions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    apolis
    -0.56
     Mohamed
    -0.56
     chariots
    -0.54
     Merseyside
    -0.54
     bantu
    -0.54
    lysses
    -0.53
    nemouth
    -0.53
     oxide
    -0.52
    '});
    -0.52
     sahaja
    -0.52
    POSITIVE LOGITS
     Iranian
    0.84
    utnik
    0.80
     Iran
    0.79
    Iran
    0.77
     Tehran
    0.76
    Iranian
    0.73
     iran
    0.71
    Yii
    0.67
    ValueStyle
    0.66
     Persian
    0.65
    Act Density 0.036%

    No Known Activations