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

    Neuronpedia

    INDEX
    Explanations

    terms related to stealthy actions or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.74
    WriteTagHelper
    -0.54
    ║
    -0.45
     potentially
    -0.45
     conceptually
    -0.44
     deemed
    -0.43
    ênes
    -0.42
    <eos>
    -0.42
    回
    -0.41
    有
    -0.41
    POSITIVE LOGITS
    zarchiwizowane
    0.77
    MessageTagHelper
    0.76
    RetentionPolicy
    0.75
    mặt
    0.74
    LookAnd
    0.73
    iastes
    0.73
    ReusableCell
    0.73
    ensement
    0.73
    DoubleQuotes
    0.71
    kháu
    0.70
    Act Density 0.190%

    No Known Activations