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

    Neuronpedia

    INDEX
    Explanations

    something vaguely like "the [NOUN]" or "[NOUN] and the" and "the [ADJ] [NOUN]". Perhaps it's looking for headings in an article

    oai_token-act-pair · gemini-2.0-flash

    recurring phrases and proper nouns

    np_token-act-pair-logits · gpt-4o-mini

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.88
    ագրություններ
    -0.77
     للمعارف
    -0.76
    ⓧ
    -0.76
    offsetof
    -0.69
    +#+#
    -0.68
     invokingState
    -0.68
     photolibrary
    -0.66
     lenker
    -0.66
     becauſe
    -0.66
    POSITIVE LOGITS
     Case
    0.54
     Last
    0.49
     We
    0.48
     See
    0.48
     Making
    0.47
     Most
    0.47
     making
    0.47
    วัติ
    0.46
     Way
    0.46
     All
    0.45
    Act Density 1.535%

    No Known Activations