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

    Neuronpedia

    INDEX
    Explanations

    references to biases and bias-related concepts

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

    bias in circuits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.66
    GTCX
    -0.63
    arangay
    -0.59
     resourceCulture
    -0.53
     للمعارف
    -0.53
     noDo
    -0.52
    enablog
    -0.52
    ypal
    -0.52
     dieſem
    -0.52
    mpagne
    -0.51
    POSITIVE LOGITS
    bias
    0.93
    biases
    0.85
    Bias
    0.77
     bias
    0.76
     Bias
    0.69
     biases
    0.61
    biased
    0.57
    BIAS
    0.56
     biased
    0.51
     biais
    0.37
    Act Density 0.093%

    No Known Activations