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

    Neuronpedia

    INDEX
    Explanations

    technical terms or jargon related to information technology and various conditions or situations that are conceptually incongruous in some way

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with evaluation and classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anon
    -0.68
    quart
    -0.64
     Polo
    -0.63
     Cheong
    -0.62
     Atkinson
    -0.62
     Spears
    -0.62
     dove
    -0.61
     Panther
    -0.60
     Beaver
    -0.60
     Christy
    -0.59
    POSITIVE LOGITS
    itably
    1.35
    uably
    1.25
    uable
    1.17
    itable
    1.17
    inately
    1.15
    ivable
    1.11
    ably
    1.10
    urable
    1.08
    orable
    1.06
    icably
    1.06
    Act Density 0.087%

    No Known Activations