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

    Neuronpedia

    INDEX
    Explanations

    events involving violence or significant actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     �
    -0.69
     REUTERS
    -0.65
     recently
    -0.63
    uesday
    -0.62
     Actress
    -0.61
     bible
    -0.61
     Presbyterian
    -0.61
     Valent
    -0.61
     James
    -0.61
     bestselling
    -0.61
    POSITIVE LOGITS
    acters
    0.82
    elo
    0.75
    tarians
    0.72
    swer
    0.71
    glers
    0.70
    eters
    0.70
    sylv
    0.68
    aez
    0.66
    rity
    0.65
    eers
    0.64
    Act Density 2.357%

    No Known Activations