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

    Neuronpedia

    INDEX
    Explanations

    references to scientific studies and citations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )did
    -0.15
    íĮIJ
    -0.15
    ì´Ī
    -0.15
    iros
    -0.14
     ÙĪرز
    -0.14
    assa
    -0.14
    ìĿij
    -0.14
    OKIE
    -0.14
    urret
    -0.13
    \Active
    -0.13
    POSITIVE LOGITS
    agi
    0.16
    emachine
    0.15
    ulty
    0.15
    plies
    0.15
     loose
    0.14
     NFS
    0.14
    701
    0.14
     appropri
    0.13
    gram
    0.13
    usch
    0.13
    Act Density 0.054%

    No Known Activations