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

    Neuronpedia

    INDEX
    Explanations

    terms related to sample data and sampling sizes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.83
    DispatchToProps
    -0.71
     fuoco
    -0.70
     StatefulWidget
    -0.64
     Beh
    -0.64
    ziem
    -0.63
     Leth
    -0.61
     StatelessWidget
    -0.60
     Ush
    -0.58
    Cyfarwyddwr
    -0.58
    POSITIVE LOGITS
     Samples
    1.72
     samples
    1.70
     SAMPLE
    1.57
     Sample
    1.55
    Samples
    1.53
    samples
    1.53
    Sample
    1.48
     sample
    1.46
     Samp
    1.41
    SAMPLE
    1.41
    Act Density 0.076%

    No Known Activations