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

    Neuronpedia

    INDEX
    Explanations

    specific types of names or proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irit
    -0.17
    ãĥ©ãĥĥãĤ¯
    -0.16
    ACES
    -0.16
    snap
    -0.15
    ucken
    -0.14
    orest
    -0.14
     ÄĮer
    -0.14
    abel
    -0.14
    лаб
    -0.14
    åŃĿ
    -0.14
    POSITIVE LOGITS
    jamin
    0.18
    olv
    0.16
    idders
    0.15
    çīĻ
    0.15
     Washer
    0.15
    me
    0.15
    ongan
    0.14
    318
    0.14
    vre
    0.14
    105
    0.14
    Act Density 0.132%

    No Known Activations