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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or organizations followed by a possessive form

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the plural form of a noun

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rounds
    -0.68
     Rothschild
    -0.63
    Prime
    -0.63
     Ago
    -0.62
    PN
    -0.62
    Balt
    -0.62
    bench
    -0.61
    Sand
    -0.61
    esp
    -0.61
    Pak
    -0.61
    POSITIVE LOGITS
    ELF
    1.14
    selves
    1.07
     own
    1.00
     namesake
    0.99
    self
    0.85
    lightly
    0.83
     finances
    0.83
     mascot
    0.82
     selves
    0.80
    outhern
    0.78
    Act Density 0.132%

    No Known Activations