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

    Neuronpedia

    INDEX
    Explanations

    verbs related to reversal or alteration

    oai_token-act-pair · gpt-3.5-turbo

    references to actions of reversing or canceling previous decisions or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ategories
    -0.86
    oak
    -0.85
    croft
    -0.77
    fighter
    -0.74
    azines
    -0.73
    metics
    -0.72
    android
    -0.70
    medium
    -0.70
    colo
    -0.69
    raq
    -0.69
    POSITIVE LOGITS
     undo
    1.28
    undo
    1.07
     undone
    1.02
     undermin
    0.77
     revers
    0.73
    ĸļ
    0.72
    issance
    0.72
     wrench
    0.71
     erase
    0.70
     miracles
    0.70
    Act Density 0.006%

    No Known Activations