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

    Neuronpedia

    INDEX
    Explanations

    negations and contradictory statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ente
    -0.15
    ilha
    -0.15
    sko
    -0.14
    gren
    -0.14
    gan
    -0.14
    nes
    -0.14
    venes
    -0.14
    avl
    -0.13
    alo
    -0.13
    .WinForms
    -0.13
    POSITIVE LOGITS
    forth
    0.18
    lify
    0.17
    theless
    0.17
    umber
    0.17
    ìĦĿ
    0.16
    ĶåĽŀ
    0.16
    ptune
    0.15
    weg
    0.15
    soever
    0.15
    orage
    0.14
    Act Density 0.023%

    No Known Activations