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

    Neuronpedia

    INDEX
    Explanations

    closures or endings of captions or articles

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Close"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¼
    -0.75
    stood
    -0.75
    ãĤ¶
    -0.71
    saf
    -0.70
    Ö¼
    -0.69
    imens
    -0.66
    values
    -0.66
    iary
    -0.65
    ãĤ©
    -0.65
    代
    -0.65
    POSITIVE LOGITS
     SHARES
    0.84
    yip
    0.71
     Bulk
    0.67
     arming
    0.67
     Loading
    0.64
     Copyright
    0.63
     Cancel
    0.63
     Delete
    0.62
     Gallery
    0.61
     Skip
    0.60
    Act Density 0.030%

    No Known Activations