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

    Neuronpedia

    INDEX
    Explanations

    terms related to content categorization and management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inding
    -0.15
    aket
    -0.14
    atform
    -0.14
    ictim
    -0.14
    ewriter
    -0.14
    phere
    -0.14
    οκ
    -0.14
    ifact
    -0.14
    nip
    -0.14
    رÙī
    -0.14
    POSITIVE LOGITS
    iously
    0.18
    editable
    0.18
    enko
    0.18
    -Length
    0.18
    Disposition
    0.18
    ieux
    0.18
    hel
    0.17
    -Type
    0.17
    hab
    0.16
    .ContextCompat
    0.16
    Act Density 0.013%

    No Known Activations