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

    Neuronpedia

    INDEX
    Explanations

    names or words related to individuals, especially those that include the substring "Sm" followed by another character

    oai_token-act-pair · gpt-3.5-turbo

    words related to physical actions or states involving chewing or biting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quarters
    -0.71
    emetery
    -0.69
     CFR
    -0.64
     Airl
    -0.63
     Triangle
    -0.63
     Smithsonian
    -0.59
     Skydragon
    -0.58
     Cortex
    -0.58
     Overse
    -0.58
     slot
    -0.57
    POSITIVE LOGITS
    iland
    0.89
    puff
    0.85
    rill
    0.83
    inki
    0.79
    opol
    0.78
    grass
    0.77
    auga
    0.76
    ify
    0.76
    glers
    0.75
    ifiers
    0.75
    Act Density 0.077%

    No Known Activations