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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" and related verbal phrases that indicate direction or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .protobuf
    -0.15
    /REC
    -0.15
    achuset
    -0.14
    aje
    -0.14
    Å¡k
    -0.14
    /assert
    -0.14
    ãĥªãĥ¼ãĤº
    -0.14
     çİ°
    -0.13
    fak
    -0.13
    oria
    -0.13
    POSITIVE LOGITS
    822
    0.15
     veteran
    0.15
     chez
    0.14
    247
    0.14
    è¶Ĭ
    0.14
    _dup
    0.14
    Ç
    0.14
    ÑĥÑĤи
    0.13
    825
    0.13
    unes
    0.13
    Act Density 0.013%

    No Known Activations