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

    Neuronpedia

    INDEX
    Explanations

    scientific or technical terms with the suffix "-agnosia"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to a specific type of disorder or syndrome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Proposition
    -0.68
    BOOK
    -0.67
    BOX
    -0.66
    PLA
    -0.63
    TING
    -0.62
    ting
    -0.61
    KEN
    -0.60
    MER
    -0.60
    FORE
    -0.60
     Ralph
    -0.58
    POSITIVE LOGITS
    agn
    1.42
    ostic
    1.26
    ificent
    1.17
    ostics
    1.08
    ados
    0.99
    itude
    0.93
    abbit
    0.91
    amine
    0.87
    olia
    0.87
    ocent
    0.87
    Act Density 0.006%

    No Known Activations