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

    Neuronpedia

    INDEX
    Explanations

    instances of commentary related to various subjects or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wikipedia
    -0.78
    ulic
    -0.76
    bis
    -0.75
    rir
    -0.68
     Hyder
    -0.67
     Sabha
    -0.66
     Dill
    -0.66
    bang
    -0.65
    hew
    -0.65
     Cov
    -0.64
    POSITIVE LOGITS
     commentary
    1.02
    ariat
    0.74
     concerning
    0.70
     analy
    0.69
     cartoons
    0.69
     analys
    0.69
     boards
    0.68
    ature
    0.67
    aries
    0.67
     commentator
    0.67
    Act Density 0.011%

    No Known Activations