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

    Neuronpedia

    INDEX
    Explanations

    words related to programming functions or methods

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ſelf
    -1.01
     iſt
    -0.99
    ſelves
    -0.96
     myſelf
    -0.93
     Theſe
    -0.92
     itſelf
    -0.89
     themſelves
    -0.85
     himſelf
    -0.84
     Majefty
    -0.84
     leaſt
    -0.81
    POSITIVE LOGITS
     
    1.04
    enterOuterAlt
    0.74
     “
    0.66
    tréal
    0.66
    featureID
    0.64
    sizeCache
    0.63
    Diwedd
    0.63
    льника
    0.62
    disposing
    0.60
     Dr
    0.59
    Act Density 0.402%

    No Known Activations