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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "ignore" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gynhyrchwyd
    -0.64
    PullParser
    -0.62
     {}'.
    -0.59
    MigrationBuilder
    -0.59
    bodyParser
    -0.58
    transQ
    -0.58
     endl
    -0.58
     {}".
    -0.58
    featureID
    -0.58
    Portale
    -0.57
    POSITIVE LOGITS
     ignore
    2.38
     ignoring
    2.18
     Ignore
    2.11
     ignores
    2.10
     ignored
    2.08
    ignore
    1.99
    Ignore
    1.76
     disregard
    1.72
     Ignoring
    1.70
     avoid
    1.68
    Act Density 0.107%

    No Known Activations