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

    Neuronpedia

    INDEX
    Explanations

    negative qualifiers and words indicating limitation or restriction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anzi
    -0.16
    amina
    -0.14
    annies
    -0.14
    lian
    -0.13
    ãĤĦãģĻ
    -0.13
     glo
    -0.13
    AMI
    -0.13
    teri
    -0.13
    å¼¥
    -0.13
    /fs
    -0.13
    POSITIVE LOGITS
    enville
    0.17
    rych
    0.14
    ethyst
    0.14
    dük
    0.14
    emean
    0.14
    umba
    0.14
    inki
    0.13
    PLE
    0.13
    åĽº
    0.13
    oggler
    0.13
    Act Density 0.092%

    No Known Activations