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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sembler
    -0.07
    aries
    -0.07
    ahoma
    -0.06
    neau
    -0.06
    bsolute
    -0.06
    ctal
    -0.06
    .Never
    -0.06
    irror
    -0.06
    aro
    -0.06
     itself
    -0.06
    POSITIVE LOGITS
    DTD
    0.09
    ÅĻad
    0.08
     æ¤
    0.07
    ensi
    0.07
    untas
    0.07
    ElapsedTime
    0.07
    ÙĪØ«
    0.07
    ä»
    0.06
    οÏħν
    0.06
    èĹ
    0.06
    Act Density 0.021%

    No Known Activations