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

    Neuronpedia

    INDEX
    Explanations

    phrases with the word "shocked" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    expressions of shock or astonishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     navig
    -0.72
     govern
    -0.72
    entry
    -0.70
    hered
    -0.69
     allotted
    -0.67
     holder
    -0.66
     reorgan
    -0.65
    uld
    -0.64
    storage
    -0.64
     governed
    -0.62
    POSITIVE LOGITS
    OUS
    0.85
    aneously
    0.85
    ingly
    0.83
    ously
    0.82
    imaru
    0.78
    ous
    0.76
    wcs
    0.73
    FUL
    0.71
    faced
    0.70
    DAQ
    0.69
    Act Density 0.066%

    No Known Activations