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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns, possessive pronouns, and referencing words

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "any" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     understandably
    -0.71
     then
    -0.59
     Amph
    -0.58
    rogens
    -0.57
     also
    -0.57
     thus
    -0.54
     Armory
    -0.53
     Emacs
    -0.52
     Tent
    -0.52
     now
    -0.52
    POSITIVE LOGITS
    abouts
    1.21
    Else
    1.15
    chard
    0.98
    nam
    0.94
    depending
    0.92
    phans
    0.90
     equivalent
    0.90
     combination
    0.89
    acle
    0.85
     Marketable
    0.82
    Act Density 0.299%

    No Known Activations