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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate comparisons or contrasts within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.64
     azok
    -0.49
    <eos>
    -0.48
    )))))
    -0.46
    ↵↵
    -0.45
    **********/
    -0.45
    </strong>
    -0.44
    】
    -0.43
    したのが
    -0.43
    :])
    -0.42
    POSITIVE LOGITS
     BoxFit
    1.21
    BeginContext
    1.07
    SourceChecksum
    1.01
     незавершена
    0.90
     autorytatywna
    0.89
    ArgsConstructor
    0.87
    expandindo
    0.87
    CloseOperation
    0.86
    تقاوى
    0.85
     Courant
    0.81
    Act Density 0.491%

    No Known Activations