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

    Neuronpedia

    INDEX
    Explanations

    references to memorandums and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    URED
    -0.18
    icity
    -0.17
    gel
    -0.16
    olley
    -0.16
    hesive
    -0.16
    entar
    -0.15
    endor
    -0.15
    eng
    -0.15
    enne
    -0.15
    jour
    -0.14
    POSITIVE LOGITS
    abilia
    0.42
    ials
    0.32
    andum
    0.27
    izing
    0.27
    ably
    0.26
    ization
    0.26
    ized
    0.26
    izes
    0.24
    anda
    0.24
    izable
    0.24
    Act Density 0.005%

    No Known Activations