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

    Neuronpedia

    INDEX
    Explanations

    expressions of hesitation or discomfort

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uada
    -0.15
    zeÅĦ
    -0.15
    erras
    -0.15
    TES
    -0.15
    STA
    -0.14
    esson
    -0.14
    inning
    -0.14
    oft
    -0.14
    rof
    -0.14
    .toInt
    -0.14
    POSITIVE LOGITS
     about
    0.21
    about
    0.17
    /ros
    0.15
     tentang
    0.15
     sharing
    0.15
    About
    0.15
     approaching
    0.15
    евеÑĢ
    0.14
    /conf
    0.14
    /an
    0.14
    Act Density 0.066%

    No Known Activations