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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing size or quality

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that express descriptions or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iphate
    -0.73
    othal
    -0.70
    ioxide
    -0.68
    aminer
    -0.68
     Ratt
    -0.66
    ript
    -0.64
     Shore
    -0.63
    LEASE
    -0.63
    ynthesis
    -0.62
    RPG
    -0.62
    POSITIVE LOGITS
    etheless
    1.06
     amounts
    1.04
    ly
    1.02
     enough
    0.98
     ones
    0.97
     quantities
    0.92
     observers
    0.89
    nesses
    0.89
    ially
    0.88
     versions
    0.85
    Act Density 0.492%

    No Known Activations