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

    Neuronpedia

    INDEX
    Explanations

    intellectual or technical terms containing special characters like accents and symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters and non-standard text elements, likely indicating formatting issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -1.08
     guiActiveUnfocused
    -0.81
    ORED
    -0.70
     decomp
    -0.68
     Electronics
    -0.62
     nexus
    -0.62
    wagen
    -0.62
    creen
    -0.61
    ified
    -0.61
    bucks
    -0.61
    POSITIVE LOGITS
    ģ
    1.33
    Ģ
    1.20
    ¬
    1.18
    ¤
    1.18
    ĭ
    1.16
    ļ
    1.16
    ´
    1.16
    ½
    1.15
    ĺ
    1.15
    ¸
    1.14
    Act Density 0.014%

    No Known Activations