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

    Neuronpedia

    INDEX
    Explanations

    words related to proper nouns, particularly names and locations

    oai_token-act-pair · gpt-3.5-turbo

    specific letters or characters appearing repeatedly in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     conscience
    -0.70
    llah
    -0.68
    OPLE
    -0.66
    merce
    -0.65
     FTA
    -0.64
     Pwr
    -0.62
     PROC
    -0.59
     ACTIONS
    -0.59
    ãģ®éŃĶ
    -0.59
     tumble
    -0.58
    POSITIVE LOGITS
    heed
    1.01
    uania
    0.91
    ttle
    0.91
    cious
    0.85
    emort
    0.84
    ounge
    0.84
    vel
    0.84
    achev
    0.81
    warm
    0.79
    ansk
    0.79
    Act Density 0.086%

    No Known Activations