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

    Neuronpedia

    INDEX
    Explanations

    specific named entities, particularly organizations or companies

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of organizations and brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ividual
    -0.78
    ++++++++++++++++
    -0.72
     aisle
    -0.72
    ------------------------------------------------
    -0.71
    âĹ¼
    -0.69
    vironment
    -0.69
    eanor
    -0.67
     rush
    -0.65
    isites
    -0.63
     carrier
    -0.63
    POSITIVE LOGITS
    Nap
    0.81
    iva
    0.69
     Golf
    0.67
    acia
    0.67
    OTOS
    0.66
     Tours
    0.64
    Var
    0.63
     Beh
    0.62
    Op
    0.61
    nil
    0.61
    Act Density 0.256%

    No Known Activations