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

    Neuronpedia

    INDEX
    Explanations

    names and identifiers of political figures or officials and their associated titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mergeFrom
    -0.72
    abetes
    -0.65
    PyExc
    -0.62
    IVEREF
    -0.58
     ImportError
    -0.57
     الرياضيه
    -0.57
    Bakgrunnsstoff
    -0.55
    usermodel
    -0.55
     unknownFields
    -0.54
     مشين
    -0.54
    POSITIVE LOGITS
     disclosure
    0.52
    ⓧ
    0.52
     accordingly
    0.50
     disclosed
    0.48
     disclosures
    0.48
     TAMBIÉN
    0.47
     kasarigan
    0.47
    ontale
    0.47
     kolei
    0.46
    berra
    0.45
    Act Density 0.031%

    No Known Activations