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

    Neuronpedia

    INDEX
    Explanations

    instances where the text expresses surprise or being surprised

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "surprised" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alach
    -0.77
    interstitial
    -0.73
    ngth
    -0.73
    ciplinary
    -0.72
    amins
    -0.72
    bern
    -0.70
    utf
    -0.70
    ignty
    -0.70
    itte
    -0.68
    haar
    -0.67
    POSITIVE LOGITS
     Squid
    0.71
     enough
    0.71
    vale
    0.69
    ãĤ¦ãĤ¹
    0.69
     aback
    0.67
     Pew
    0.67
    >>>
    0.67
    cules
    0.65
     how
    0.65
     Dragonbound
    0.64
    Act Density 0.029%

    No Known Activations