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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "until."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÚĺÙĨ
    -0.16
    ãĥ³ãĤ¹
    -0.15
    osit
    -0.15
     بخ
    -0.15
     Seks
    -0.15
    Wunused
    -0.15
    krv
    -0.14
    声ãĤĴ
    -0.14
    oenix
    -0.14
    çĪµ
    -0.14
    POSITIVE LOGITS
    zier
    0.19
     until
    0.17
     Till
    0.16
    ting
    0.15
     ret
    0.15
    Until
    0.15
     Until
    0.15
     inform
    0.15
     till
    0.15
     informed
    0.14
    Act Density 0.045%

    No Known Activations