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

    Neuronpedia

    INDEX
    Explanations

    references to horses and their related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]]:
    -0.86
    fromUtf
    -0.84
    ]]
    -0.80
    mew
    -0.77
    }<\
    -0.74
    ]**
    -0.74
    ]").
    -0.73
    ))).
    -0.73
    gridColumn
    -0.73
    ]].
    -0.72
    POSITIVE LOGITS
    horses
    1.07
     horse
    0.96
     Horses
    0.95
     horses
    0.95
    Horses
    0.95
    didSet
    0.92
    horse
    0.92
     HORSE
    0.88
     chevaux
    0.88
    Horse
    0.84
    Act Density 0.320%

    No Known Activations