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

    Neuronpedia

    INDEX
    Explanations

    personal names and locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.88
    ancial
    -0.67
    inatory
    -0.66
    iosity
    -0.64
    matically
    -0.63
    atural
    -0.63
    £ı
    -0.62
    INGTON
    -0.62
    selves
    -0.61
    ourcing
    -0.60
    POSITIVE LOGITS
    ño
    1.44
    lli
    1.42
    lda
    1.33
    lla
    1.30
    xt
    1.27
    llo
    1.27
    cker
    1.24
    gger
    1.24
    lled
    1.22
    cki
    1.22
    Act Density 0.387%

    No Known Activations