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

    Neuronpedia

    INDEX
    Explanations

    minerals or chemical compounds

    oai_token-act-pair · gpt-3.5-turbo

    instances of the suffix "ite."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aido
    -0.91
    ntil
    -0.89
     carbohyd
    -0.87
    aii
    -0.87
    orsi
    -0.83
    ersive
    -0.80
    etheless
    -0.79
    enhagen
    -0.78
    abulary
    -0.78
    merce
    -0.76
    POSITIVE LOGITS
    ite
    1.02
    eer
    0.77
    geist
    0.75
    lli
    0.70
    fish
    0.67
    WHERE
    0.66
    chnology
    0.65
    os
    0.64
     Scotia
    0.64
     Tiger
    0.63
    Act Density 0.012%

    No Known Activations