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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing frustration and anger

    oai_token-act-pair · gpt-3.5-turbo

    emotional expressions and reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.86
    xtap
    -0.81
    upon
    -0.72
    prisingly
    -0.71
    ometimes
    -0.70
    surprisingly
    -0.70
    ItemImage
    -0.65
    uitive
    -0.64
     :=
    -0.64
    mittedly
    -0.63
    POSITIVE LOGITS
    ',"
    1.81
    !'"
    1.77
    '."
    1.76
    '"
    1.68
    .")
    1.67
    ,'"
    1.66
    .'"
    1.61
    ").
    1.59
    ?'"
    1.58
    ').
    1.52
    Act Density 0.880%

    No Known Activations