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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "bias" and its related forms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    bias of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.56
    interesting
    -0.47
     royaume
    -0.44
    MCM
    -0.43
     Royaume
    -0.42
    NgModule
    -0.42
    henden
    -0.41
     ویکی‌پدی
    -0.41
     veritable
    -0.41
    manchester
    -0.41
    POSITIVE LOGITS
     bias
    2.56
     Bias
    2.42
    bias
    2.25
    Bias
    2.20
     biases
    1.95
    BIAS
    1.80
     biased
    1.76
    biased
    1.63
    biases
    1.55
     Bia
    1.20
    Act Density 0.018%

    No Known Activations