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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "surely" in the text

    oai_token-act-pair · gpt-3.5-turbo

    the word "surely" to indicate certainty or assurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enture
    -0.59
    gon
    -0.59
    aca
    -0.59
    pat
    -0.55
    act
    -0.53
    irection
    -0.53
    ento
    -0.53
    oresc
    -0.52
     Southwest
    -0.52
    us
    -0.52
    POSITIVE LOGITS
     surely
    3.55
     doubtless
    2.39
     undoubtedly
    2.22
     certainly
    2.03
     Surely
    1.92
     evidently
    1.66
     inevitably
    1.64
     definitely
    1.50
     probably
    1.42
     presumably
    1.42
    Act Density 0.018%

    No Known Activations