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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations, particularly related to probability distributions and estimators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.74
     not
    -0.57
     in
    -0.56
    ,
    -0.56
     l
    -0.55
     (
    -0.55
     P
    -0.54
     “
    -0.54
    ’
    -0.54
     U
    -0.53
    POSITIVE LOGITS
    ²
    1.21
    ².
    1.11
    :✨
    1.11
    ³
    1.10
    ²,
    1.08
    .³
    1.05
     feroit
    1.04
    OGND
    1.00
    IsMutable
    0.99
     auroit
    0.99
    Act Density 0.402%

    No Known Activations