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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing choice and decision-making

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

    Followed by "can", "must", "may", or "are"

    np_acts-logits-general · gemini-2.0-flash

    you followed by modal verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    だが
    -0.90
    だったが
    -0.86
    であるが
    -0.80
     بتوان
    -0.76
    이다
    -0.66
     kita
    -0.66
    ようだ
    -0.65
    fromCharCode
    -0.64
     صوتيه
    -0.63
     dirinya
    -0.62
    POSITIVE LOGITS
     yourself
    2.71
     your
    2.13
    yourself
    2.01
     yourselves
    1.98
     Yourself
    1.82
     YOURSELF
    1.76
    your
    1.74
    Yourself
    1.44
    Your
    1.40
     Your
    1.27
    Act Density 1.346%

    No Known Activations