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

    Neuronpedia

    INDEX
    Explanations

    the word "forget" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the words "forget," "forgot," and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amen
    -0.67
    berus
    -0.66
     coefficients
    -0.66
    orough
    -0.65
    Ec
    -0.65
    inals
    -0.64
    XY
    -0.64
    elled
    -0.62
    é¾
    -0.62
    tained
    -0.61
    POSITIVE LOGITS
    fulness
    1.16
    fully
    1.06
    ful
    1.03
    ingly
    0.78
    lore
    0.78
     forgetting
    0.77
     forgot
    0.77
    noon
    0.77
    ening
    0.75
    remember
    0.74
    Act Density 0.022%

    No Known Activations