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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "ignore" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roderick
    -0.68
     Fuku
    -0.62
    )(((
    -0.61
     EconPapers
    -0.61
     valmis
    -0.60
    TRAVEL
    -0.59
    SUCCEEDED
    -0.59
    ္
    -0.59
    publique
    -0.59
     fær
    -0.58
    POSITIVE LOGITS
     ignore
    1.99
     ignored
    1.91
     ignoring
    1.89
     ignores
    1.85
     Ignore
    1.83
    ignore
    1.65
     Ignoring
    1.59
     ignor
    1.58
    Ignoring
    1.52
    ignored
    1.49
    Act Density 0.143%

    No Known Activations