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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to information technology and electronics

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to physical objects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wise
    -0.81
    roo
    -0.61
    lessly
    -0.60
    cation
    -0.58
    atever
    -0.58
    ERAL
    -0.56
    cipled
    -0.55
    OUS
    -0.55
    iage
    -0.55
    ornia
    -0.54
    POSITIVE LOGITS
     themselves
    1.64
    '
    1.62
    ']
    1.28
    '"
    1.17
    ',"
    1.12
    ',
    1.07
    ')
    1.06
    hip
    1.04
    '."
    1.03
    '.
    1.02
    Act Density 0.440%

    No Known Activations