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

    Neuronpedia

    INDEX
    Explanations

    references to graduation and related academic milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.20
    dra
    -0.19
    帯
    -0.17
    bons
    -0.16
    i
    -0.16
    itter
    -0.15
    gres
    -0.15
    iw
    -0.15
    endra
    -0.15
    akter
    -0.14
    POSITIVE LOGITS
    uates
    0.42
    uation
    0.40
    uating
    0.39
    uate
    0.38
    uated
    0.37
    uations
    0.30
    ually
    0.28
    ual
    0.26
    ute
    0.25
    IENT
    0.22
    Act Density 0.005%

    No Known Activations