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

    Neuronpedia

    INDEX
    Explanations

    occurrences of citations and references in academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ech
    -0.17
    nten
    -0.15
    زار
    -0.15
    eb
    -0.15
    jak
    -0.15
     Higgins
    -0.14
    achten
    -0.14
    pector
    -0.14
    peater
    -0.14
     foreground
    -0.14
    POSITIVE LOGITS
    istrovstvÃŃ
    0.20
    ozo
    0.15
     Lage
    0.15
    /device
    0.14
    íĻĪ
    0.13
    poons
    0.13
    oth
    0.13
     yat
    0.13
     Earn
    0.13
    /providers
    0.13
    Act Density 0.005%

    No Known Activations