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

    Neuronpedia

    INDEX
    Explanations

    instances of introductory phrases or transitions in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owing
    -0.21
    paring
    -0.21
    give
    -0.19
    plevel
    -0.19
    ses
    -0.17
    $MESS
    -0.17
    serrat
    -0.17
    complete
    -0.17
    uffix
    -0.16
    leccion
    -0.16
    POSITIVE LOGITS
    odore
    0.64
    adays
    0.63
    etheless
    0.54
    atre
    0.46
    bsites
    0.41
    ÑįÑĤомÑĥ
    0.40
    atomy
    0.39
    xiety
    0.36
    tlement
    0.36
    greSQL
    0.34
    Act Density 1.193%

    No Known Activations