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

    Neuronpedia

    INDEX
    Explanations

    verbs related to physical actions

    oai_token-act-pair · gpt-3.5-turbo

    dynamic actions or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĨĴ
    -0.72
     Chili
    -0.70
    ritic
    -0.67
     Helic
    -0.65
    eli
    -0.63
     Uni
    -0.63
     diagn
    -0.61
     Nobel
    -0.60
     Billion
    -0.60
    Downloadha
    -0.59
    POSITIVE LOGITS
    up
    0.89
     up
    0.88
    away
    0.86
    aways
    0.81
    aded
    0.78
     ashore
    0.75
     away
    0.73
    wash
    0.72
    ups
    0.72
     off
    0.71
    Act Density 0.217%

    No Known Activations