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

    Neuronpedia

    INDEX
    Explanations

    structures related to conditional or imperative statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idel
    -0.18
     Yard
    -0.16
    rio
    -0.15
    ĶåĽŀ
    -0.14
    cale
    -0.14
    conv
    -0.14
     sabot
    -0.14
     sab
    -0.14
     Horton
    -0.14
    nave
    -0.14
    POSITIVE LOGITS
    imat
    0.17
    .Companion
    0.16
     wÅĤa
    0.16
    Ú©ÙĪر
    0.16
    infeld
    0.16
    nga
    0.15
    795
    0.15
    rouch
    0.15
    lush
    0.14
    .runner
    0.14
    Act Density 0.002%

    No Known Activations