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

    Neuronpedia

    INDEX
    Explanations

    the word "was" indicating past tense narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    806
    -0.17
     Laz
    -0.16
     Tet
    -0.15
    itz
    -0.15
    oug
    -0.15
    751
    -0.14
    this
    -0.14
    ida
    -0.14
    639
    -0.14
    redd
    -0.14
    POSITIVE LOGITS
     Swinger
    0.15
    ób
    0.14
    éĺ³åŁİ
    0.14
    лини
    0.14
    Msp
    0.14
    gesi
    0.14
    cka
    0.14
    «ĺ
    0.14
    Ø®ÙĬ
    0.14
    Recognizer
    0.14
    Act Density 0.005%

    No Known Activations