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

    Neuronpedia

    INDEX
    Explanations

    the word "be" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases beginning with "don't be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inally
    -0.86
    yip
    -0.84
     Enhancement
    -0.75
    ciation
    -0.73
     hail
    -0.69
     notch
    -0.69
    ordes
    -0.68
    plings
    -0.66
    ciating
    -0.65
    ¶
    -0.64
    POSITIVE LOGITS
     confused
    1.06
     bothered
    1.06
     fooled
    1.02
     mistaken
    0.98
     intimidated
    0.97
     underestimated
    0.95
     ashamed
    0.95
     swayed
    0.92
     afraid
    0.91
     alarmed
    0.91
    Act Density 0.100%

    No Known Activations