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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "no" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.81
    ,
    -0.74
    ?
    -0.74
    /
    -0.73
    !
    -0.72
    m
    -0.69
    f
    -0.68
    e
    -0.68
    :
    -0.68
    i
    -0.67
    POSITIVE LOGITS
    ^(@)
    1.09
    verwijspagina
    1.05
    noinspection
    1.01
    ₂+
    1.00
    modelBuilder
    1.00
    hoeddwyd
    0.99
    >\<^
    0.98
    ItemBackground
    0.91
    %")
    0.88
    etheless
    0.86
    Act Density 0.084%

    No Known Activations