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

    Neuronpedia

    INDEX
    Explanations

    expressions of commitment or dedication

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

    committed to or committing acts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anskje
    -0.46
    getLength
    -0.46
     pleaſure
    -0.46
     Einsch
    -0.44
    audience
    -0.43
     laziness
    -0.43
    parseFloat
    -0.43
    eway
    -0.42
    Audience
    -0.42
    OrNull
    -0.42
    POSITIVE LOGITS
     committed
    2.06
    committed
    1.84
     Committed
    1.83
    Committed
    1.66
     commit
    1.41
     commits
    1.34
     Commit
    1.30
     COMMIT
    1.27
    commit
    1.26
     committing
    1.23
    Act Density 0.006%

    No Known Activations