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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize the impact or significance of specific actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cæsar
    -0.77
     uſed
    -0.71
     himſelf
    -0.67
     pleaſure
    -0.66
     purpoſe
    -0.65
     raiſ
    -0.65
     Atiku
    -0.64
     eiffel
    -0.64
     fevere
    -0.63
     Addis
    -0.62
    POSITIVE LOGITS
     the
    1.23
     OF
    1.10
    .}(
    1.01
     Of
    1.01
    .)}
    0.95
     a
    0.93
     their
    0.91
     sorts
    0.90
    MessageOf
    0.88
     our
    0.88
    Act Density 1.430%

    No Known Activations