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

    Neuronpedia

    INDEX
    Explanations

    capitalized prepositions or articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocamp
    -0.69
    rouse
    -0.63
    seless
    -0.63
    geist
    -0.61
    oat
    -0.61
    ffen
    -0.59
    ingly
    -0.59
    enges
    -0.59
    inator
    -0.59
    inges
    -0.58
    POSITIVE LOGITS
    MAN
    1.30
    VIEW
    1.25
    COL
    1.17
    VILLE
    1.17
    TON
    1.12
     THERE
    1.12
    LAND
    1.12
    PORT
    1.11
    VERS
    1.11
     CITY
    1.08
    Act Density 0.025%

    No Known Activations