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

    Neuronpedia

    INDEX
    Explanations

    references to boxes and related concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufs
    -0.16
    ufen
    -0.16
    urre
    -0.16
    zon
    -0.15
    WebHost
    -0.15
    ourn
    -0.15
     Mug
    -0.15
    ustrial
    -0.14
    urence
    -0.14
    ORIZ
    -0.14
    POSITIVE LOGITS
    (es
    0.33
    score
    0.26
    ercise
    0.26
    <dyn
    0.25
    elder
    0.24
    scores
    0.24
    ers
    0.23
    -sizing
    0.23
    xes
    0.23
    -office
    0.22
    Act Density 0.025%

    No Known Activations