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

    Neuronpedia

    INDEX
    Explanations

    concepts related to scientific terminology and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gebn
    -0.15
     Hend
    -0.14
     vod
    -0.14
    åĽ½
    -0.14
    ìłĪ
    -0.14
     обла
    -0.13
     defe
    -0.13
     Shack
    -0.13
     Mö
    -0.13
    vod
    -0.13
    POSITIVE LOGITS
     freeze
    0.29
     fire
    0.26
     Freeze
    0.25
    freeze
    0.24
     Ur
    0.21
    .fire
    0.20
     FIRE
    0.20
     wounded
    0.20
     centr
    0.20
    çģ«
    0.19
    Act Density 0.003%

    No Known Activations