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

    Neuronpedia

    INDEX
    Explanations

    references to protests and demonstrations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ChildScrollView
    -0.86
     Lik
    -0.74
     Crud
    -0.68
    Darius
    -0.67
    disposition
    -0.65
     Jad
    -0.62
    vician
    -0.62
     likeness
    -0.61
    Lik
    -0.61
     lap
    -0.61
    POSITIVE LOGITS
     Protest
    1.25
     protest
    1.18
    protest
    1.16
     protests
    1.12
    Protest
    1.09
     protested
    1.05
     protes
    1.04
     protesting
    0.92
     protester
    0.91
     protesters
    0.88
    Act Density 0.004%

    No Known Activations