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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating various forms of action or requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ffa
    -0.16
    ĽĪ
    -0.15
    TestCategory
    -0.15
    agogue
    -0.15
    شت
    -0.14
    usercontent
    -0.14
    pires
    -0.14
    idth
    -0.14
    jedn
    -0.14
    :///
    -0.14
    POSITIVE LOGITS
     cue
    0.30
     beating
    0.28
     liking
    0.28
     cues
    0.28
     step
    0.24
     stance
    0.24
     shine
    0.24
     toll
    0.23
     look
    0.23
     risks
    0.23
    Act Density 0.055%

    No Known Activations