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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology and projects

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols that may represent certain themes or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.79
     Seym
    -0.72
     detached
    -0.71
     Dupl
    -0.66
     Wand
    -0.66
     guiActiveUnfocused
    -0.65
     Opera
    -0.65
     destro
    -0.65
     Niet
    -0.64
    itaire
    -0.62
    POSITIVE LOGITS
    ª
    1.11
    IJ
    1.09
    Ĵ
    1.03
    «
    1.02
    ij
    1.02
    certain
    0.95
    their
    0.94
    ı
    0.92
    once
    0.91
    say
    0.90
    Act Density 0.149%

    No Known Activations