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

    Neuronpedia

    INDEX
    Explanations

    sequences containing a specific combination of special characters and letters

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ethnicity or cultural identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GCC
    -0.69
     Blow
    -0.66
     Chevron
    -0.64
     Suz
    -0.64
     Bengal
    -0.64
     Newfoundland
    -0.64
     reinforcement
    -0.62
     structure
    -0.62
     clicks
    -0.61
     Queens
    -0.61
    POSITIVE LOGITS
    ti
    1.40
    nik
    1.30
    eh
    1.27
    e
    1.23
    ek
    1.17
    kov
    1.15
    lich
    1.15
    til
    1.15
    dra
    1.14
    ev
    1.11
    Act Density 0.034%

    No Known Activations