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

    Neuronpedia

    INDEX
    Explanations

    constructs related to scoring and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sip
    -0.16
    ilon
    -0.16
    933
    -0.15
     Sutton
    -0.15
    cken
    -0.14
     Sunder
    -0.14
     Stefan
    -0.14
    Smarty
    -0.14
    mant
    -0.13
    ServletContext
    -0.13
    POSITIVE LOGITS
     score
    0.70
     scores
    0.63
    score
    0.60
    -score
    0.59
     Score
    0.58
    _score
    0.55
    Score
    0.54
    .score
    0.54
    -sc
    0.53
    scores
    0.52
    Act Density 0.102%

    No Known Activations