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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to different environments or settings

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to different aspects of the world and experiences within it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ificantly
    -0.80
    ificant
    -0.76
     Important
    -0.69
    icut
    -0.68
    orthy
    -0.67
    ivably
    -0.64
    Important
    -0.62
    risome
    -0.62
    illy
    -0.61
    volent
    -0.61
    POSITIVE LOGITS
     afforded
    0.84
    antry
    0.81
     of
    0.77
     surrounding
    0.69
     confines
    0.69
    ounters
    0.69
     backdrop
    0.68
    behind
    0.67
     depicted
    0.67
    smanship
    0.66
    Act Density 0.542%

    No Known Activations