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

    Neuronpedia

    INDEX
    Explanations

    references to dowries and towels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nova
    -0.21
    REAM
    -0.19
    nis
    -0.19
    ouser
    -0.18
    nell
    -0.17
    WOOD
    -0.17
    ually
    -0.17
    erot
    -0.16
    nov
    -0.16
    jeme
    -0.16
    POSITIVE LOGITS
    icz
    0.32
    orld
    0.26
    ls
    0.25
    ksi
    0.23
    ww
    0.22
    itzer
    0.21
    www
    0.21
    ohl
    0.21
    ey
    0.20
    itness
    0.20
    Act Density 0.066%

    No Known Activations