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

    Neuronpedia

    INDEX
    Explanations

    references to a specific technology or concept, likely related to programming or data processing, that has a strong impact

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or category labeled 'X'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    getic
    -0.87
    cffff
    -0.70
    Ú
    -0.70
    ¢
    -0.70
     captcha
    -0.68
     stru
    -0.68
    kson
    -0.66
     behavi
    -0.66
     Pru
    -0.64
     beh
    -0.61
    POSITIVE LOGITS
    avier
    1.37
    peria
    1.32
    cellence
    1.15
    VII
    1.03
    iao
    1.02
    III
    1.01
    press
    0.98
    posed
    0.98
    eon
    0.97
    ternal
    0.94
    Act Density 0.031%

    No Known Activations