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

    Neuronpedia

    INDEX
    Explanations

    instances of hesitation or uncertainty in speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shepherd
    -0.15
    rex
    -0.15
     Andersen
    -0.15
    weighted
    -0.14
    icer
    -0.14
    intl
    -0.14
    ellow
    -0.14
    dds
    -0.13
    verity
    -0.13
     wat
    -0.13
    POSITIVE LOGITS
    _managed
    0.17
     Residence
    0.15
    evi
    0.15
    uster
    0.15
     Bren
    0.14
    ¢
    0.14
    anky
    0.14
    jab
    0.14
    .scalablytyped
    0.13
    ä¾Ľ
    0.13
    Act Density 0.023%

    No Known Activations