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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "thinking" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lero
    -0.08
    legate
    -0.07
    agna
    -0.06
    ppard
    -0.06
    akest
    -0.06
     nejd
    -0.06
    ì§Ī
    -0.06
    ëŁŃ
    -0.06
    aign
    -0.06
    ÏĦαι
    -0.06
    POSITIVE LOGITS
     Outside
    0.07
     outside
    0.07
     cap
    0.07
    ÐĴÐŀ
    0.07
     Bout
    0.06
    cap
    0.06
    ach
    0.06
     about
    0.06
    è¿Ľ
    0.06
    iability
    0.06
    Act Density 0.005%

    No Known Activations