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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text after periods and commas

    np_acts-logits-general · gemini-2.0-flash

    pronouns and articles after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.95
     myſelf
    -0.93
     Monfieur
    -0.89
     purpoſe
    -0.89
     ſeveral
    -0.84
     pleaſure
    -0.83
     himſelf
    -0.81
     Theſe
    -0.78
     uſe
    -0.76
    EDEFAULT
    -0.76
    POSITIVE LOGITS
    這位
    0.88
    这位
    0.84
     the
    0.66
     The
    0.58
     he
    0.55
    WebServlet
    0.52
     pemuda
    0.49
     pria
    0.48
     He
    0.46
     Ma
    0.45
    Act Density 0.164%

    No Known Activations