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

    Neuronpedia

    INDEX
    Explanations

    instances of the prefix "non-" indicating negation or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.32
     myſelf
    -1.21
     itſelf
    -1.18
     chofe
    -1.13
     Monfieur
    -1.12
     Anſ
    -1.12
     Majefty
    -1.09
     becauſe
    -1.09
     ainfi
    -1.08
     uſed
    -1.08
    POSITIVE LOGITS
     inter
    0.97
     trans
    0.86
     Trans
    0.78
     Inter
    0.75
     lead
    0.70
     
    0.67
    Trans
    0.65
     mat
    0.65
     real
    0.65
     cross
    0.65
    Act Density 0.188%

    No Known Activations