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

    Neuronpedia

    INDEX
    Explanations

    references to attacks and assaults

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erator
    -0.17
    idenav
    -0.15
    cales
    -0.15
     oku
    -0.15
    ấy
    -0.15
    ones
    -0.15
    cin
    -0.15
    autoload
    -0.15
    ullets
    -0.15
    ÑĨем
    -0.14
    POSITIVE LOGITS
    ive
    0.21
    ively
    0.20
    tiv
    0.19
    able
    0.18
    ademic
    0.17
    iveness
    0.17
    ainment
    0.15
    &T
    0.15
    NOWLED
    0.15
    e
    0.15
    Act Density 0.039%

    No Known Activations