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

    Neuronpedia

    INDEX
    Explanations

    phrases related to examining or discussing something in detail

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    trap
    -0.73
    externalActionCode
    -0.72
    Cry
    -0.70
    arak
    -0.67
    Skill
    -0.67
    nown
    -0.67
    bur
    -0.67
    widget
    -0.66
    enthal
    -0.66
    DON
    -0.65
    POSITIVE LOGITS
     how
    0.79
     them
    0.77
     these
    0.73
     pictures
    0.73
     what
    0.73
     the
    0.73
     whats
    0.71
     positives
    0.69
     things
    0.69
    awed
    0.68
    Act Density 0.063%

    No Known Activations