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

    Neuronpedia

    INDEX
    Explanations

    words related to technical details and specifications

    oai_token-act-pair · gpt-3.5-turbo

    plural nouns related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     arts
    -0.60
    OSP
    -0.59
    atalie
    -0.58
    ESCO
    -0.56
    quickShipAvailable
    -0.56
    leans
    -0.55
     fringe
    -0.55
    eneg
    -0.54
    anan
    -0.53
     prejudice
    -0.53
    POSITIVE LOGITS
    kaya
    1.25
    ourcing
    1.09
    ourced
    1.02
    linger
    1.00
    leeve
    0.95
    wered
    0.95
    ucker
    0.92
    mith
    0.89
    icle
    0.89
    manship
    0.87
    Act Density 0.104%

    No Known Activations