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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate authorship or the means by which something is accomplished

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahat
    -0.14
    rello
    -0.14
    .sz
    -0.14
    avenport
    -0.13
    ccak
    -0.13
    icari
    -0.13
    lavÃŃ
    -0.13
    voy
    -0.13
    AFX
    -0.13
    IDX
    -0.13
    POSITIVE LOGITS
     being
    0.22
     virtue
    0.18
     means
    0.17
    ung
    0.17
     having
    0.16
    olan
    0.16
     mand
    0.15
    being
    0.15
    apy
    0.15
     not
    0.15
    Act Density 0.070%

    No Known Activations