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

    Neuronpedia

    INDEX
    Explanations

    actions related to legal or administrative processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itura
    -0.16
    izzo
    -0.15
    xis
    -0.15
    reative
    -0.14
    uci
    -0.14
    idor
    -0.14
     abstraction
    -0.14
    ÄŁe
    -0.14
    _DISK
    -0.14
    cie
    -0.13
    POSITIVE LOGITS
    hook
    0.15
    emez
    0.15
    lun
    0.15
    etta
    0.14
     Hooks
    0.14
    iat
    0.14
    Ly
    0.14
    ohan
    0.14
     Feather
    0.14
    ohana
    0.13
    Act Density 0.158%

    No Known Activations