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

    Neuronpedia

    INDEX
    Explanations

    phrases related to freedom of speech

    oai_token-act-pair · gpt-3.5-turbo

    references to free speech and related legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stab
    -0.75
    rises
    -0.71
     Maz
    -0.69
     Pes
    -0.68
    ARDS
    -0.68
     Cats
    -0.67
     Jaguar
    -0.66
     Coh
    -0.65
     Cancel
    -0.64
    earth
    -0.64
    POSITIVE LOGITS
    speech
    1.09
     speech
    0.92
    ible
    0.86
    pedia
    0.85
    anchester
    0.84
     rights
    0.83
     protections
    0.81
    anooga
    0.79
    edIn
    0.77
     liberties
    0.76
    Act Density 0.028%

    No Known Activations