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

    Neuronpedia

    INDEX
    Explanations

    technical terms or acronyms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "for" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inese
    -0.68
    illin
    -0.67
     jaws
    -0.64
    Tube
    -0.58
    âĶ
    -0.56
    erous
    -0.56
     vom
    -0.56
    marine
    -0.56
     beware
    -0.55
    ttle
    -0.55
    POSITIVE LOGITS
    bidden
    1.51
    gotten
    1.50
    ced
    1.04
     example
    1.04
    WARD
    1.02
    cing
    1.01
     instance
    1.01
    give
    0.99
    gery
    0.99
    bid
    0.97
    Act Density 0.095%

    No Known Activations