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

    Neuronpedia

    INDEX
    Explanations

    mentions of protests or demonstrations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "demonstrator" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     multif
    -0.69
     daddy
    -0.66
    STEM
    -0.65
     levers
    -0.65
    WR
    -0.65
     helm
    -0.65
     versa
    -0.63
    bern
    -0.61
     alphabet
    -0.61
     curv
    -0.60
    POSITIVE LOGITS
    ants
    1.08
    ATIONS
    0.92
    ations
    0.91
    acements
    0.90
    ATION
    0.90
    adesh
    0.85
    culosis
    0.83
    icken
    0.83
    ators
    0.82
    isers
    0.82
    Act Density 0.042%

    No Known Activations