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

    Neuronpedia

    INDEX
    Explanations

    sentences expressing a negative viewpoint or disagreement

    oai_token-act-pair · gpt-3.5-turbo

    negations and expressions of inability or lack

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ription
    -0.74
    lesi
    -0.70
    plates
    -0.69
    plate
    -0.68
    rys
    -0.67
    pora
    -0.67
    andan
    -0.66
    odium
    -0.65
    istrates
    -0.65
    alian
    -0.64
    POSITIVE LOGITS
     darn
    0.77
    èª
    0.74
    Õ
    0.74
    \\\\
    0.72
    æĦ
    0.67
    íķ
    0.66
    ãģł
    0.66
    âķIJ
    0.66
    Availability
    0.65
    ifiable
    0.65
    Act Density 0.063%

    No Known Activations