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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the potential or possibility of something happening

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate potential or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ing
    -0.69
    washer
    -0.61
    kar
    -0.60
    building
    -0.57
     Cortex
    -0.57
    OVA
    -0.57
    ging
    -0.56
     honors
    -0.56
    furt
    -0.56
    Maker
    -0.55
    POSITIVE LOGITS
     feas
    1.20
    ĸļ
    1.07
    berra
    1.05
    adian
    1.01
     theoretically
    0.96
     conclud
    0.96
     conce
    0.95
    ÃĥÃĤ
    0.92
     tremend
    0.91
     hypot
    0.88
    Act Density 0.089%

    No Known Activations