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

    Neuronpedia

    INDEX
    Explanations

    references to popular culture characters and themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lings
    -0.16
    arding
    -0.16
    verity
    -0.15
     ent
    -0.15
    .dy
    -0.14
    EDITOR
    -0.14
    odic
    -0.14
    EDIT
    -0.14
    ë£
    -0.14
    etros
    -0.14
    POSITIVE LOGITS
    locker
    0.18
    ovat
    0.16
    dig
    0.15
    LOCKS
    0.14
    вед
    0.14
    ÙĬÙĨÙĬ
    0.14
     Scar
    0.14
    Hub
    0.14
    geo
    0.14
     Blaze
    0.14
    Act Density 0.021%

    No Known Activations