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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negation or limitation in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     -
    -0.84
    ,
    -0.78
     a
    -0.75
    .
    -0.71
    :
    -0.69
     the
    -0.68
     –
    -0.67
    -
    -0.66
     et
    -0.62
     of
    -0.62
    POSITIVE LOGITS
    +#+#
    1.05
    ########.
    1.02
     tslint
    0.99
    ".
    0.98
     Савезне
    0.94
    httphttps
    0.93
     Мексичка
    0.90
     ་་
    0.90
    ✨:
    0.90
     $_"
    0.89
    Act Density 0.487%

    No Known Activations