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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "to" and phrases indicating intent or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĤин
    -0.14
    _eof
    -0.14
    tie
    -0.14
    addon
    -0.14
     Stevenson
    -0.13
    acus
    -0.13
    طر
    -0.13
    ë°
    -0.13
     mans
    -0.13
    ÙģÙĨ
    -0.13
    POSITIVE LOGITS
     see
    0.17
    ibri
    0.17
    raquo
    0.16
    yz
    0.15
     yourselves
    0.15
    ILES
    0.15
     yourself
    0.15
     Rack
    0.15
    ç«ĭ
    0.15
    amedi
    0.14
    Act Density 0.037%

    No Known Activations