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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bender
    -0.16
     Thick
    -0.15
    éħ¸
    -0.14
    uru
    -0.14
    iac
    -0.14
    rtle
    -0.14
     Schneider
    -0.14
    WARE
    -0.14
    YYY
    -0.14
    á»ĵ
    -0.14
    POSITIVE LOGITS
     synthetic
    0.21
    Ljava
    0.19
     Synthetic
    0.17
    oux
    0.17
    zioni
    0.15
    ektiv
    0.15
    .dex
    0.15
     ginger
    0.14
    лож
    0.14
    DEX
    0.14
    Act Density 0.005%

    No Known Activations