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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "here."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ses
    -0.19
    -era
    -0.15
    ss
    -0.15
    aurant
    -0.15
    ãĤ«ãĥ¼
    -0.15
    nt
    -0.15
    sex
    -0.15
    thin
    -0.14
    .toInt
    -0.14
    iture
    -0.14
    POSITIVE LOGITS
    after
    0.31
    abouts
    0.27
    ina
    0.26
    unto
    0.21
    jÅ¡ÃŃ
    0.21
    under
    0.20
    upon
    0.20
    INA
    0.18
    fore
    0.17
    langs
    0.17
    Act Density 0.070%

    No Known Activations