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

    Neuronpedia

    INDEX
    Explanations

    mentions of locations or people

    oai_token-act-pair · gpt-3.5-turbo

    the word "as" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Trident
    -0.57
    OUGH
    -0.57
     Sting
    -0.57
    Submit
    -0.56
     Sussex
    -0.55
     Squid
    -0.55
     thumbnail
    -0.55
     complete
    -0.53
     Drift
    -0.52
    ships
    -0.52
    POSITIVE LOGITS
    daq
    1.23
    aurus
    1.22
    cius
    1.19
    semble
    1.15
    pora
    1.15
    adena
    1.11
    ylum
    1.10
    utra
    1.10
    bestos
    1.10
    iewicz
    1.09
    Act Density 0.083%

    No Known Activations