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

    Neuronpedia

    INDEX
    Explanations

    phrases related to potential outcomes or consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest potential consequences or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    teen
    -0.72
    cloth
    -0.67
    washer
    -0.67
    raining
    -0.66
    raint
    -0.62
    cies
    -0.62
    core
    -0.60
    got
    -0.59
     honors
    -0.59
    Maker
    -0.59
    POSITIVE LOGITS
     feas
    1.28
     conce
    1.25
     be
    1.04
     potentially
    1.02
     possibly
    0.98
     tremend
    0.97
     theoretically
    0.96
     hypot
    0.96
     someday
    0.94
    berra
    0.94
    Act Density 0.090%

    No Known Activations