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

    Neuronpedia

    INDEX
    Explanations

    mentions of the name "Harlan" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ess
    -0.21
    else
    -0.20
    y
    -0.20
    ij
    -0.20
    iard
    -0.20
    ene
    -0.19
    esc
    -0.18
    ias
    -0.18
    escal
    -0.18
    ka
    -0.17
    POSITIVE LOGITS
    low
    0.17
    mony
    0.17
    riers
    0.17
    eri
    0.16
    ÅĽnie
    0.16
    -right
    0.16
    ullo
    0.16
    vey
    0.16
    thur
    0.16
    riet
    0.16
    Act Density 0.014%

    No Known Activations