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

    Neuronpedia

    INDEX
    Explanations

    references to books

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    most
    -0.16
    MENT
    -0.16
    monds
    -0.15
    ept
    -0.15
    igm
    -0.15
    ally
    -0.14
    ifter
    -0.14
    apons
    -0.14
    ator
    -0.14
    abb
    -0.14
    POSITIVE LOGITS
    ç±į
    0.36
    shelf
    0.34
    worm
    0.29
    ends
    0.29
    keeping
    0.28
    stores
    0.26
    ellers
    0.25
    eller
    0.25
    -length
    0.24
    lets
    0.24
    Act Density 0.064%

    No Known Activations