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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter "t" in the middle of words

    oai_token-act-pair · gpt-3.5-turbo

    contractions of the word "not"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SetTextColor
    -0.80
    éĹĺ
    -0.69
    士
    -0.69
     Lines
    -0.65
    ership
    -0.64
     Devices
    -0.63
     Moves
    -0.62
     Reloaded
    -0.62
    Ĥİ
    -0.60
    tips
    -0.60
    POSITIVE LOGITS
     necessarily
    1.02
    withstanding
    1.00
    ional
    0.94
    ople
    0.94
     entirely
    0.91
    ournament
    0.90
     exactly
    0.86
    entimes
    0.86
    azed
    0.84
     terribly
    0.82
    Act Density 0.046%

    No Known Activations