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

    Neuronpedia

    INDEX
    Explanations

    phrases where something is categorized or labeled as something specific

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "as" followed by different descriptors or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reiterate
    -0.68
    Length
    -0.68
    raq
    -0.66
    imize
    -0.66
    atl
    -0.63
    itiveness
    -0.63
    awar
    -0.62
    auldron
    -0.62
    width
    -0.62
    scenes
    -0.62
    POSITIVE LOGITS
     belonging
    0.95
     follows
    0.92
    pers
    0.81
    criptions
    0.76
     opposed
    0.76
    pires
    0.75
     conscientious
    0.74
    pired
    0.74
     having
    0.72
     well
    0.71
    Act Density 0.112%

    No Known Activations