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

    Neuronpedia

    INDEX
    Explanations

    references to individuals' personal backgrounds and qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wendell
    -0.61
     logical
    -0.60
    Parms
    -0.58
    scary
    -0.58
     connotation
    -0.58
     resumption
    -0.58
     reversal
    -0.58
     Gub
    -0.58
     schlaf
    -0.58
     forgiven
    -0.58
    POSITIVE LOGITS
     has
    1.14
     was
    1.11
     had
    1.08
     will
    1.07
     is
    1.06
     have
    0.97
     could
    0.91
     would
    0.87
     must
    0.86
     can
    0.85
    Act Density 0.324%

    No Known Activations