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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating time or points in a discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     overnight
    -0.16
     Tal
    -0.15
    owie
    -0.15
    gart
    -0.15
    pute
    -0.15
    loff
    -0.14
     dirty
    -0.14
    -0.14
    chk
    -0.14
    mes
    -0.14
    POSITIVE LOGITS
    tank
    0.16
    andise
    0.15
    .VisualBasic
    0.15
    655
    0.15
     ëıĮ
    0.15
    atoon
    0.14
    :`~
    0.14
    wise
    0.14
    hausen
    0.13
    ãģ¾ãģł
    0.13
    Act Density 0.028%

    No Known Activations