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

    Neuronpedia

    INDEX
    Explanations

    terms related to clerical positions or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pills
    -0.15
    e
    -0.15
    tte
    -0.15
    ersh
    -0.15
    yat
    -0.15
    560
    -0.14
    ille
    -0.14
    eve
    -0.14
    aska
    -0.14
    anmar
    -0.14
    POSITIVE LOGITS
    ical
    0.22
    ks
    0.20
    gy
    0.18
    mont
    0.18
     cler
    0.17
    ihan
    0.17
    ics
    0.17
    kin
    0.17
    king
    0.16
    lero
    0.16
    Act Density 0.006%

    No Known Activations