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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions suggesting relationships or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gether
    -0.33
    oriously
    -0.29
    ably
    -0.28
    ingly
    -0.27
    sembled
    -0.27
    leep
    -0.27
    wards
    -0.27
    pects
    -0.26
    olated
    -0.25
    oretical
    -0.25
    POSITIVE LOGITS
    sy
    0.22
    eri
    0.22
    ses
    0.22
    sip
    0.21
    ml
    0.21
    dl
    0.21
    tem
    0.20
    s
    0.19
    cel
    0.19
    ker
    0.19
    Act Density 0.118%

    No Known Activations