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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oppers
    -0.16
    ãģ¤ãģij
    -0.15
    soever
    -0.15
    rug
    -0.15
    éĸĭ
    -0.15
    erd
    -0.14
    è¦ĭ
    -0.14
    oulder
    -0.14
    m
    -0.14
    raise
    -0.14
    POSITIVE LOGITS
    gether
    0.33
    /from
    0.31
    plevel
    0.24
    ledo
    0.20
    wner
    0.20
    ying
    0.19
    tes
    0.19
    ogle
    0.19
    asts
    0.19
    tems
    0.19
    Act Density 1.208%

    No Known Activations