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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to processes or activities

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to various academic or technical fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cmp
    -0.67
     è£ı
    -0.64
     thereof
    -0.62
     drum
    -0.61
     cough
    -0.61
     impart
    -0.60
     monopoly
    -0.59
     phosphate
    -0.58
     turkey
    -0.58
    *.
    -0.58
    POSITIVE LOGITS
    atically
    0.96
    ificantly
    0.93
    ortunately
    0.89
    itionally
    0.87
    hetically
    0.87
    itably
    0.86
    inarily
    0.81
    ationally
    0.81
    atic
    0.80
    ivably
    0.80
    Act Density 0.232%

    No Known Activations