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

    Neuronpedia

    INDEX
    Explanations

    references to literary culture and famous authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reh
    -0.16
    tember
    -0.15
    imuth
    -0.15
     Orleans
    -0.15
    CF
    -0.15
    fang
    -0.14
     ves
    -0.14
     Jenner
    -0.14
    enschaft
    -0.14
     Barbar
    -0.14
    POSITIVE LOGITS
     Joyce
    0.40
     Dublin
    0.39
    Joy
    0.30
     Bloom
    0.29
     Irish
    0.27
    Dub
    0.26
     Ireland
    0.26
     Blo
    0.25
     Stephen
    0.24
    Blo
    0.24
    Act Density 0.005%

    No Known Activations