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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to time

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the token "0"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     symp
    -0.72
     ener
    -0.71
     challeng
    -0.71
     pse
    -0.68
    forth
    -0.68
     indo
    -0.66
    milo
    -0.66
    ei
    -0.63
     coerc
    -0.62
     stru
    -0.62
    POSITIVE LOGITS
     SHARES
    1.44
     Shares
    1.03
     Expand
    0.78
     Explicit
    0.77
     Ratings
    0.69
     Comments
    0.68
     Investig
    0.68
     Clean
    0.67
     Arrest
    0.67
     Detected
    0.64
    Act Density 0.019%

    No Known Activations