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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing beliefs, opinions, and moral judgments

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

    Follows the word "is" or "be"

    np_acts-logits-general · gemini-2.0-flash

    be/is + descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.92
    WithIOException
    -0.86
     ModelExpression
    -0.82
    GEBURTSDATUM
    -0.80
    +#+#
    -0.78
     CreateTagHelper
    -0.75
     estimés
    -0.71
    protoimpl
    -0.70
     propOrder
    -0.70
    AndEndTag
    -0.68
    POSITIVE LOGITS
     akin
    0.57
     equivalent
    0.57
     like
    0.54
     tan
    0.53
     an
    0.52
    بالإنجليزية
    0.48
    outState
    0.47
    ilding
    0.47
    equivalent
    0.47
     equivale
    0.47
    Act Density 0.247%

    No Known Activations