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

    Neuronpedia

    INDEX
    Explanations

    stylistic characters or symbols, such as accented letters and unusual punctuation

    oai_token-act-pair · gpt-3.5-turbo

    specific letters or symbols within various scripts and languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     board
    -0.79
     favor
    -0.77
     panels
    -0.74
     charm
    -0.71
     overload
    -0.70
     cheer
    -0.67
     representation
    -0.67
     boards
    -0.66
     whistlebl
    -0.65
     delegates
    -0.65
    POSITIVE LOGITS
    ¹
    1.51
    Ń
    1.46
    ª
    1.42
    º
    1.42
    ²
    1.40
    ±
    1.40
    ¨
    1.38
    ¢
    1.38
    ³
    1.37
    £
    1.35
    Act Density 0.024%

    No Known Activations