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

    Neuronpedia

    INDEX
    Explanations

    references to horse racing events and participants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    down
    -0.18
     down
    -0.17
    -down
    -0.17
    _INLINE
    -0.16
    Down
    -0.15
     Bers
    -0.14
    _DOWN
    -0.14
    763
    -0.14
    _VM
    -0.14
    æ±Ĥ
    -0.14
    POSITIVE LOGITS
     trainer
    0.20
     jumps
    0.19
     Jump
    0.19
     jumping
    0.18
     connections
    0.18
     jump
    0.18
     hurd
    0.17
     declarations
    0.17
    trainer
    0.17
     stable
    0.17
    Act Density 0.022%

    No Known Activations