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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating surprise or shock

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to shock, surprise, and alarming situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nav
    -0.81
     servicing
    -0.79
     bonded
    -0.78
    ère
    -0.77
    neys
    -0.77
    claimer
    -0.76
    ney
    -0.75
    pei
    -0.74
    wright
    -0.74
    perate
    -0.73
    POSITIVE LOGITS
    ly
    1.00
     revelations
    0.92
    LY
    0.88
     Revelations
    0.88
    Trend
    0.80
     revelation
    0.78
    Fact
    0.76
     Flavoring
    0.76
     statistic
    0.74
     occurrences
    0.72
    Act Density 0.061%

    No Known Activations