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

    Neuronpedia

    INDEX
    Explanations

    negative prefixes and words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.97
     becauſe
    -0.97
     ainfi
    -0.97
     myſelf
    -0.94
     chofe
    -0.93
     Theſe
    -0.91
     Monfieur
    -0.90
     Majefty
    -0.86
     Thebes
    -0.85
     auffi
    -0.83
    POSITIVE LOGITS
     inter
    1.00
     trans
    0.87
     Inter
    0.79
     Trans
    0.75
     INTER
    0.70
    inter
    0.70
     pre
    0.69
     cross
    0.67
     multi
    0.67
    :\/\/
    0.67
    Act Density 0.216%

    No Known Activations