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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a large quantity or significance of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orns
    -0.19
    ceed
    -0.15
    iors
    -0.15
    天åłĤ
    -0.14
    pagesize
    -0.14
    μÎŃ
    -0.14
    pie
    -0.14
    halb
    -0.14
    utters
    -0.14
    hores
    -0.14
    POSITIVE LOGITS
    /all
    0.18
     of
    0.17
     Felipe
    0.16
    ofire
    0.15
    olt
    0.15
     happening
    0.15
     Shields
    0.15
    endar
    0.14
    822
    0.14
    angent
    0.14
    Act Density 0.060%

    No Known Activations