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

    Neuronpedia

    INDEX
    Explanations

    references to algorithms used in a computational or statistical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mCurrent
    -0.48
    ))/
    -0.46
    erover
    -0.45
     never
    -0.42
    Mister
    -0.42
     Mister
    -0.42
    ])/
    -0.41
    }}}
    -0.41
    ]),
    -0.41
     refra
    -0.40
    POSITIVE LOGITS
     algorithm
    0.95
     Algorithm
    0.85
     alpha
    0.84
    alpha
    0.82
    Algorithm
    0.80
     Alpha
    0.77
    algorithm
    0.76
    Alpha
    0.76
    算法
    0.72
    beta
    0.71
    Act Density 0.216%

    No Known Activations