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

    Neuronpedia

    INDEX
    Explanations

    questions involving the action of doing or knowing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entai
    -0.16
    iná
    -0.16
    nar
    -0.15
     Hearth
    -0.14
    lab
    -0.14
    bef
    -0.13
    queued
    -0.13
    دÙĩ
    -0.13
    pecies
    -0.13
    AIL
    -0.13
    POSITIVE LOGITS
    eres
    0.18
    rosse
    0.15
    çį²
    0.15
    Ŀ
    0.15
     prove
    0.15
     get
    0.15
    otp
    0.14
    kaar
    0.14
    žel
    0.14
    Uvs
    0.14
    Act Density 0.075%

    No Known Activations