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

    Neuronpedia

    INDEX
    Explanations

    references to collaborative workshops and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arr
    -0.17
    ehr
    -0.15
    eyer
    -0.15
    ARR
    -0.14
    ohon
    -0.14
    anco
    -0.14
    ousand
    -0.14
    èħ¹
    -0.14
    urring
    -0.13
    822
    -0.13
    POSITIVE LOGITS
    彦
    0.15
    PPER
    0.15
    IGH
    0.14
    lider
    0.14
     dereg
    0.14
    pper
    0.14
     $č↵
    0.14
    dere
    0.14
    aping
    0.13
    GAME
    0.13
    Act Density 0.244%

    No Known Activations