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

    Neuronpedia

    INDEX
    Explanations

    phrases or words indicating a standout or important feature

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "highlight" and related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ldon
    -0.86
    llah
    -0.78
    avement
    -0.78
    sil
    -0.75
    perate
    -0.73
    nee
    -0.73
    yss
    -0.71
    atern
    -0.71
    aah
    -0.69
    nery
    -0.68
    POSITIVE LOGITS
     highlights
    1.12
    TextColor
    1.01
     reel
    0.98
     highlight
    0.91
     Highlights
    0.85
     highlighting
    0.81
     showc
    0.79
     reminders
    0.78
     showcases
    0.77
    ãĤ¤ãĥĪ
    0.74
    Act Density 0.007%

    No Known Activations