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

    Neuronpedia

    INDEX
    Explanations

    special characters, likely from a particular language or code

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols that may indicate formatting or encoding issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -1.19
    schild
    -0.74
     guiActiveUnfocused
    -0.74
     decomp
    -0.73
     dividing
    -0.65
     flash
    -0.64
    creen
    -0.62
     Conrad
    -0.62
     Electronics
    -0.62
     multipl
    -0.61
    POSITIVE LOGITS
    ģ
    1.37
    ¤
    1.27
    Ĩ
    1.27
    ļ
    1.26
    ¢
    1.26
    ´
    1.25
    ĺ
    1.24
    ¬
    1.24
    ĭ
    1.20
    »
    1.20
    Act Density 0.021%

    No Known Activations