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

    Neuronpedia

    INDEX
    Explanations

    instances of confidence and certainty within a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    StandardItem
    -0.15
     beden
    -0.14
    wor
    -0.14
    umi
    -0.14
    ês
    -0.14
    .MouseAdapter
    -0.14
    ei
    -0.14
    iek
    -0.14
    inyin
    -0.14
    ddf
    -0.13
    POSITIVE LOGITS
    atten
    0.15
    ValueCollection
    0.15
    923
    0.14
     lux
    0.14
    rich
    0.14
    this
    0.13
    airo
    0.13
     Katz
    0.13
    egers
    0.13
    ecz
    0.13
    Act Density 0.234%

    No Known Activations