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

    Neuronpedia

    INDEX
    Explanations

    different types of things

    oai_token-act-pair · gpt-3.5-turbo

    mentions of different categories or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rame
    -0.69
    Led
    -0.67
    pire
    -0.66
    wark
    -0.65
    charge
    -0.63
    wash
    -0.63
    lest
    -0.62
    oyer
    -0.61
    endum
    -0.61
    imate
    -0.61
    POSITIVE LOGITS
     types
    3.59
    types
    2.70
     kinds
    2.61
     type
    2.51
     Types
    2.49
    Types
    2.28
    type
    1.90
     sorts
    1.87
    Type
    1.72
     varieties
    1.67
    Act Density 0.013%

    No Known Activations