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

    Neuronpedia

    INDEX
    Explanations

    references to clerical work or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tte
    -0.15
    osta
    -0.15
    ille
    -0.15
    ersh
    -0.15
    e
    -0.15
    HD
    -0.15
    anmar
    -0.14
     chilled
    -0.14
    yses
    -0.14
    HR
    -0.14
    POSITIVE LOGITS
    ical
    0.26
    gy
    0.21
    ks
    0.20
    ihan
    0.18
    mont
    0.18
    ics
    0.18
    kin
    0.18
    ken
    0.17
    king
    0.17
    ovnÃŃ
    0.16
    Act Density 0.005%

    No Known Activations