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

    Neuronpedia

    INDEX
    Explanations

    measurements and dimensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     equal
    -0.17
    is
    -0.17
     Darren
    -0.16
     Dawn
    -0.16
    -0.16
     deg
    -0.16
     Hugh
    -0.15
     alt
    -0.15
     until
    -0.15
    ness
    -0.15
    POSITIVE LOGITS
    -sized
    0.22
    Ïįν
    0.19
     sized
    0.18
    tatus
    0.18
    inki
    0.18
    ĥn
    0.18
    ç´ļ
    0.17
    ayacak
    0.17
    -Length
    0.16
     Sized
    0.16
    Act Density 0.183%

    No Known Activations