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

    Neuronpedia

    INDEX
    Explanations

    locations or institutions related to education

    oai_token-act-pair · gpt-3.5-turbo

    references to specific places and people, particularly academic institutions and notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odes
    -0.85
    士
    -0.81
     metic
    -0.76
    izes
    -0.76
     cylinders
    -0.74
    ACTED
    -0.70
     externalToEVAOnly
    -0.69
     resil
    -0.68
     notor
    -0.68
     ingred
    -0.68
    POSITIVE LOGITS
     Beir
    1.05
    stad
    0.93
    terson
    0.87
    rik
    0.84
     Hav
    0.82
    pole
    0.80
    riks
    0.80
    ritz
    0.79
    ument
    0.75
     Heidi
    0.74
    Act Density 0.022%

    No Known Activations