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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and references to ownership or authorship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fuse
    -0.16
    istrovstvÃŃ
    -0.15
     tato
    -0.14
    alse
    -0.14
    ussy
    -0.14
    bee
    -0.14
    èĭ±æĸĩ
    -0.14
    stroy
    -0.14
     Bris
    -0.14
     Rivera
    -0.13
    POSITIVE LOGITS
     approach
    0.17
    rens
    0.16
     proposal
    0.16
    utan
    0.15
    eph
    0.15
     findings
    0.15
    earer
    0.15
    POSITE
    0.14
    gre
    0.14
     colleague
    0.14
    Act Density 0.138%

    No Known Activations