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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" and variations of "to work."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yyn
    -0.15
    ERM
    -0.15
     Fior
    -0.15
    urance
    -0.14
    Æ¡
    -0.14
    .fromFunction
    -0.14
    Åĵ
    -0.14
     Stra
    -0.14
    onth
    -0.14
    BM
    -0.13
    POSITIVE LOGITS
     Cre
    0.16
    âĹİ
    0.14
    riott
    0.14
    holm
    0.13
    nable
    0.13
    oy
    0.13
    XC
    0.13
    niž
    0.13
    ÙĪÙĬس
    0.13
    angu
    0.13
    Act Density 0.074%

    No Known Activations