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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals, particularly those named Neil

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Harry
    -0.65
     Potter
    -0.61
     Williams
    -0.60
     Mac
    -0.59
     المر
    -0.59
     jel
    -0.59
     tub
    -0.58
     Schröder
    -0.58
     Marcell
    -0.58
    woo
    -0.57
    POSITIVE LOGITS
     Dimit
    0.81
     topaz
    0.79
     Dawes
    0.79
     crows
    0.78
    tometer
    0.76
     Dili
    0.76
     CERN
    0.76
     Dismiss
    0.75
     SwitchCompat
    0.75
     WaitForSeconds
    0.75
    Act Density 0.720%

    No Known Activations