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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "never" in various contexts indicating negation or impossibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bereits
    -0.16
    already
    -0.16
     already
    -0.16
     Äijang
    -0.16
    ä¸įæĸŃ
    -0.15
    hani
    -0.15
     Already
    -0.15
    à¸
    -0.15
    éĺħ
    -0.15
    æŃ£åľ¨
    -0.14
    POSITIVE LOGITS
    theless
    0.39
    -ending
    0.35
    -ever
    0.28
    -before
    0.27
    mind
    0.25
    ending
    0.24
     really
    0.23
     EVER
    0.21
     ce
    0.20
     quite
    0.20
    Act Density 0.049%

    No Known Activations