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

    Neuronpedia

    INDEX
    Explanations

    usages of the word "out" and related phrases suggesting removal or exclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TCR
    -0.95
    etheless
    -0.89
    theless
    -0.88
    MemoryWarning
    -0.84
    ized
    -0.82
    quelize
    -0.81
     Berna
    -0.81
    cosity
    -0.80
     AssemblyProduct
    -0.79
    TCR
    -0.78
    POSITIVE LOGITS
     OUT
    1.58
     Out
    1.45
     out
    1.43
    out
    1.43
    Out
    1.42
    OUT
    1.21
     outs
    1.18
    getOut
    1.02
     Outs
    1.00
    outs
    0.97
    Act Density 0.125%

    No Known Activations