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

    Neuronpedia

    INDEX
    Explanations

    words related to horses

    oai_token-act-pair · gpt-3.5-turbo

    references to horses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaries
    -0.98
    âĶģ
    -0.82
    unda
    -0.79
    licted
    -0.74
     newsp
    -0.72
    iary
    -0.71
    lections
    -0.69
    apse
    -0.69
    iance
    -0.69
    usal
    -0.68
    POSITIVE LOGITS
    meat
    1.09
    manship
    1.04
     Horses
    1.00
    poke
    1.00
    men
    0.98
     horses
    0.97
    fish
    0.95
    horse
    0.95
    women
    0.94
    wright
    0.93
    Act Density 0.023%

    No Known Activations