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

    Neuronpedia

    INDEX
    Explanations

    instances of uncertainty or undefined terms in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ige
    -0.17
    adow
    -0.15
    ähr
    -0.15
    INTR
    -0.14
    erb
    -0.14
     Ventures
    -0.14
    horn
    -0.14
    endor
    -0.14
    SURE
    -0.14
    #w
    -0.13
    POSITIVE LOGITS
    rina
    0.16
    isses
    0.16
    дÑı
    0.15
    Difficulty
    0.15
     lil
    0.15
    icio
    0.15
    \grid
    0.14
     ciz
    0.14
    .Mutable
    0.14
     Clair
    0.14
    Act Density 0.001%

    No Known Activations