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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "thought" and related expressions reflecting contemplation or decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lm
    -0.15
    yar
    -0.15
     currently
    -0.15
     youre
    -0.15
    acon
    -0.15
    yi
    -0.15
    ả
    -0.14
     whats
    -0.14
    Æ°á»Łng
    -0.14
     Ãĸn
    -0.14
    POSITIVE LOGITS
     surely
    0.31
     maybe
    0.28
     perhaps
    0.28
    maybe
    0.25
    perhaps
    0.25
    Sure
    0.23
    sure
    0.23
     Surely
    0.23
     Perhaps
    0.22
    Perhaps
    0.21
    Act Density 0.097%

    No Known Activations