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

    Neuronpedia

    INDEX
    Explanations

    proper nouns followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Karl" or names ending in "-arl."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dangerous
    -0.75
     NX
    -0.69
     Karma
    -0.68
    positive
    -0.66
     Called
    -0.64
    DIT
    -0.62
     MAKE
    -0.61
    flix
    -0.61
     Myth
    -0.59
    LV
    -0.59
    POSITIVE LOGITS
    atan
    1.08
    ophone
    1.04
    otta
    1.02
    otte
    0.99
    ounge
    0.98
    adium
    0.96
    owship
    0.96
    atos
    0.95
    ief
    0.94
    ings
    0.93
    Act Density 0.004%

    No Known Activations