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

    Neuronpedia

    INDEX
    Explanations

    operations and functions related to reading and writing data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gi
    -0.20
    aju
    -0.15
    lemn
    -0.15
    ok
    -0.15
    ity
    -0.14
    ugh
    -0.14
    asks
    -0.14
    lei
    -0.14
    phere
    -0.14
    yu
    -0.14
    POSITIVE LOGITS
    /write
    0.18
    robe
    0.18
    ults
    0.17
    tres
    0.17
    uka
    0.17
    /list
    0.17
    ings
    0.16
    iness
    0.16
    fulness
    0.15
    just
    0.15
    Act Density 0.037%

    No Known Activations