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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating something is surprising or unexpected

    oai_token-act-pair · gpt-3.5-turbo

    the concept of surprise associated with certain topics or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Accessed
    -0.81
    querque
    -0.79
    stream
    -0.69
    aciously
    -0.68
    interstitial
    -0.67
    bow
    -0.65
    buster
    -0.64
    vance
    -0.64
    omo
    -0.63
    estyles
    -0.63
    POSITIVE LOGITS
     me
    1.30
     outsiders
    1.13
     anyone
    1.04
     us
    1.01
     him
    0.98
     anybody
    0.97
     observers
    0.93
     everyone
    0.93
     insiders
    0.91
     many
    0.87
    Act Density 0.237%

    No Known Activations