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

    Neuronpedia

    INDEX
    Explanations

    phrases urging not to forget something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of remembering or not forgetting something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FO
    -0.67
    uana
    -0.65
    Hunt
    -0.64
    amen
    -0.60
    DE
    -0.60
    gae
    -0.59
     nomine
    -0.59
    osion
    -0.58
    Combat
    -0.58
    China
    -0.58
    POSITIVE LOGITS
    fulness
    1.11
    fully
    0.93
    ful
    0.91
     forget
    0.90
    theless
    0.90
     forgot
    0.88
     forgetting
    0.85
     remembered
    0.80
     Forget
    0.80
    bryce
    0.78
    Act Density 0.013%

    No Known Activations