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

    Neuronpedia

    INDEX
    Explanations

    the word "surprisingly" when it is used in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "surprisingly."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.84
    abad
    -0.78
    rie
    -0.72
    icipated
    -0.69
    glas
    -0.68
    iche
    -0.66
    ingham
    -0.66
    sel
    -0.66
    creation
    -0.64
    selling
    -0.63
    POSITIVE LOGITS
     surprisingly
    1.02
     surpr
    0.77
     srfAttach
    0.77
     surprising
    0.75
    atility
    0.74
    ESA
    0.74
     enough
    0.73
     remarkably
    0.71
     shockingly
    0.71
    itably
    0.71
    Act Density 0.006%

    No Known Activations