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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate ongoing actions or positions of individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ì¹Ń
    -0.16
    attery
    -0.15
    éĿ©
    -0.14
    ¬ģ
    -0.14
    inished
    -0.13
    çĪ±
    -0.13
     conver
    -0.13
     Propel
    -0.13
    agree
    -0.13
    endez
    -0.13
    POSITIVE LOGITS
     continue
    0.45
     continues
    0.43
     continued
    0.43
     continuing
    0.42
    continue
    0.40
    continued
    0.39
     continu
    0.38
    继ç»Ń
    0.36
     Continued
    0.36
    Continue
    0.35
    Act Density 0.013%

    No Known Activations