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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence or condition of something, focusing on forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    üven
    -0.16
    imits
    -0.15
     ìĤ¬íķŃ
    -0.14
    989
    -0.14
     baÅŁÄ±na
    -0.14
    ä¿Ĺ
    -0.14
    ugg
    -0.14
    isu
    -0.14
    registers
    -0.13
    608
    -0.13
    POSITIVE LOGITS
     important
    0.19
     interesting
    0.19
    gon
    0.18
     like
    0.18
     such
    0.16
     definitely
    0.16
     very
    0.16
    oire
    0.15
    ze
    0.15
     something
    0.15
    Act Density 0.120%

    No Known Activations