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

    Neuronpedia

    INDEX
    Explanations

    technical terms and mediating processes related to software and system functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addCriterion
    -0.68
    ]--;
    -0.66
    <bos>
    -0.59
    السكان
    -0.59
    ksikon
    -0.58
     AssemblyTitle
    -0.57
    CPtr
    -0.57
    GOTREF
    -0.56
    ]();
    -0.56
    DoubleQuotes
    -0.56
    POSITIVE LOGITS
     is
    0.99
     seems
    0.94
     sounds
    0.90
     definitely
    0.89
    是非常
    0.84
    是很
    0.83
     suffices
    0.82
     certainly
    0.81
     preferable
    0.80
    seems
    0.79
    Act Density 0.539%

    No Known Activations