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

    Neuronpedia

    INDEX
    Explanations

    specific references to horses and horse racing events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ActionTypes
    -0.16
    аÑĢÑĩ
    -0.15
    ç«ĭãģ¡
    -0.15
    -chevron
    -0.14
    PLICIT
    -0.14
    ucha
    -0.14
     inne
    -0.14
    кап
    -0.14
    OLVE
    -0.14
    ovnÃŃ
    -0.14
    POSITIVE LOGITS
     horse
    0.31
     horses
    0.29
    horse
    0.24
     Horse
    0.24
     stable
    0.23
     trainer
    0.23
     rac
    0.22
    stable
    0.21
     Racing
    0.21
     Stable
    0.21
    Act Density 0.067%

    No Known Activations