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

    Neuronpedia

    INDEX
    Explanations

    names of universities and colleges

    oai_token-act-pair · gpt-3.5-turbo

    references to various universities and colleges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usting
    -0.83
    ttle
    -0.74
    eto
    -0.69
    ._
    -0.68
    erity
    -0.66
    retty
    -0.64
    vous
    -0.63
    .—
    -0.62
    ?:
    -0.61
    ura
    -0.60
    POSITIVE LOGITS
     lith
    0.66
     differential
    0.63
     FI
    0.63
     delinqu
    0.61
     cellul
    0.59
     Cyborg
    0.59
     Neph
    0.58
     hydra
    0.58
     Lith
    0.58
    phan
    0.57
    Act Density 0.271%

    No Known Activations