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

    Neuronpedia

    INDEX
    Explanations

    the beginning of sentences or paragraphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.58
    ↵↵
    -0.51
     (
    -0.48
    Anyhow
    -0.48
     …
    -0.47
     "
    -0.47
    in
    -0.45
    …
    -0.45
     I
    -0.45
    /
    -0.44
    POSITIVE LOGITS
     Мексичка
    1.16
    +#+#
    1.14
     AssemblyCulture
    1.04
     Houſe
    0.95
     Majefty
    0.94
    mybatisplus
    0.94
    ########.
    0.93
     ་་
    0.91
     Administrativna
    0.91
     للمعارف
    0.90
    Act Density 0.091%

    No Known Activations