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

    Neuronpedia

    INDEX
    Explanations

    phrases related to examining or analyzing something

    oai_token-act-pair · gpt-3.5-turbo

    references to the action of taking a look or reviewing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    trap
    -0.78
    lette
    -0.74
    cell
    -0.73
    externalActionCode
    -0.71
    soever
    -0.70
    CHO
    -0.70
    Mach
    -0.68
    isSpecialOrderable
    -0.67
    Church
    -0.65
    bender
    -0.65
    POSITIVE LOGITS
     whats
    0.85
     how
    0.79
     positives
    0.71
     puberty
    0.71
     what
    0.70
     why
    0.69
     sunset
    0.67
     the
    0.66
     least
    0.66
     highlights
    0.65
    Act Density 0.041%

    No Known Activations