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

    Neuronpedia

    INDEX
    Explanations

    references to individuals involved in political or legal controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    declaration
    -0.15
    amarin
    -0.14
    _buffers
    -0.14
     Clim
    -0.14
    anne
    -0.14
    _handles
    -0.14
    subcategory
    -0.14
    reesome
    -0.14
     increments
    -0.13
    ardless
    -0.13
    POSITIVE LOGITS
    ior
    0.17
    FI
    0.15
     groom
    0.15
    ene
    0.15
    Fi
    0.14
    ector
    0.14
     man
    0.14
    iner
    0.14
    ess
    0.14
     bund
    0.14
    Act Density 0.003%

    No Known Activations