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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing probability or expectation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acades
    -0.17
    jin
    -0.15
    sel
    -0.14
    ady
    -0.14
    igmoid
    -0.14
    related
    -0.14
    inal
    -0.13
    ãng
    -0.13
    -webpack
    -0.13
    agnet
    -0.13
    POSITIVE LOGITS
    hood
    0.23
    weise
    0.17
    ;y
    0.15
    mente
    0.15
    ilty
    0.15
     Fres
    0.14
    estar
    0.14
    ities
    0.14
    и
    0.14
    kommen
    0.14
    Act Density 0.027%

    No Known Activations