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

    Neuronpedia

    INDEX
    Explanations

    instances of testing-related terminology and function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    大åħ¨
    -0.15
    IQUE
    -0.14
    lest
    -0.14
    opus
    -0.14
     lad
    -0.14
    iton
    -0.14
    á»ĩu
    -0.13
    ços
    -0.13
    atan
    -0.13
    iling
    -0.13
    POSITIVE LOGITS
    .skip
    0.17
    .todo
    0.16
    ury
    0.15
    URY
    0.14
    _should
    0.14
    bote
    0.14
     skipped
    0.14
     behavioural
    0.14
    [][]
    0.14
     behaviour
    0.14
    Act Density 0.005%

    No Known Activations