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

    Neuronpedia

    INDEX
    Explanations

    instances of self-doubt and uncertainty in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isci
    -0.16
    elia
    -0.15
    abi
    -0.15
    cot
    -0.14
     dese
    -0.14
     vocal
    -0.14
    inda
    -0.14
    lev
    -0.14
    anda
    -0.13
    ILLE
    -0.13
    POSITIVE LOGITS
    rador
    0.16
    elden
    0.16
    asper
    0.15
    plat
    0.15
    /platform
    0.14
    üml
    0.14
    Ậ
    0.14
    peon
    0.14
    acha
    0.14
     periodic
    0.13
    Act Density 0.160%

    No Known Activations