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

    Neuronpedia

    INDEX
    Explanations

    queries or requests for help related to programming and technical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HasBeen
    -0.20
     regardless
    -0.16
     ฿
    -0.16
    ´t
    -0.15
    Regardless
    -0.15
    turnstile
    -0.15
     renown
    -0.14
    _refl
    -0.14
     succes
    -0.14
    à¥ĭà¤ĸ
    -0.14
    POSITIVE LOGITS
     till
    0.22
     mentioning
    0.20
     Till
    0.20
     mention
    0.20
    abcd
    0.19
     few
    0.18
     mentioned
    0.18
     Mention
    0.17
     compuls
    0.16
     erst
    0.16
    Act Density 0.535%

    No Known Activations