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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and operators typically used in coding syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Charlie
    -1.17
    Charlie
    -1.07
     charlie
    -1.03
     Charley
    -0.98
    charlie
    -0.91
     Manson
    -0.78
     Boone
    -0.75
     Charle
    -0.74
     Chaplin
    -0.71
     Charles
    -0.69
    POSITIVE LOGITS
     SB
    1.00
     sb
    0.97
    sb
    0.93
     Sb
    0.86
    SB
    0.85
    Sb
    0.83
     Dobbs
    0.74
     Pamp
    0.71
     Kingston
    0.70
     Andrzej
    0.69
    Act Density 0.934%

    No Known Activations