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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "into."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plen
    -0.17
    rozen
    -0.16
    VRT
    -0.15
    ÏĢλ
    -0.14
    prak
    -0.14
     Evet
    -0.14
    _stdio
    -0.14
    addin
    -0.14
    -gnu
    -0.14
    Late
    -0.13
    POSITIVE LOGITS
    onga
    0.17
    isman
    0.14
    HEY
    0.14
    tml
    0.14
    stant
    0.14
    tracted
    0.13
    isy
    0.13
     Abuse
    0.13
    iped
    0.13
     Lions
    0.13
    Act Density 0.026%

    No Known Activations