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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "forget" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mage
    -0.14
    anova
    -0.14
    549
    -0.14
    Ậ
    -0.14
    oog
    -0.14
    leness
    -0.14
    rup
    -0.14
     Bare
    -0.14
    kem
    -0.14
    wright
    -0.14
    POSITIVE LOGITS
    fulness
    0.17
    amus
    0.15
    :async
    0.15
     bid
    0.14
    ting
    0.14
    obil
    0.14
    tings
    0.14
     pit
    0.14
    /not
    0.14
    /set
    0.13
    Act Density 0.017%

    No Known Activations