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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating transitions or notes of positivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __(/*!
    -0.96
    OGND
    -0.76
     Roskov
    -0.75
    ########.
    -0.72
     EconPapers
    -0.72
    writeFieldEnd
    -0.72
    ftagPool
    -0.71
     للاسماء
    -0.69
     mergeFrom
    -0.67
    Sucesor
    -0.67
    POSITIVE LOGITS
     note
    1.52
     Note
    1.16
    note
    1.13
    Note
    1.08
     NOTE
    1.04
     related
    1.03
    余談
    1.03
     notes
    1.03
     siden
    1.02
     aside
    0.94
    Act Density 0.329%

    No Known Activations