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

    Neuronpedia

    INDEX
    Explanations

    terms related to political and social movements or actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political and social advocacy or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.75
     undermin
    -0.60
    renheit
    -0.57
    milo
    -0.57
    abwe
    -0.57
    Lago
    -0.56
    arettes
    -0.56
    jri
    -0.53
    itored
    -0.53
    ecause
    -0.52
    POSITIVE LOGITS
    iest
    0.76
     portion
    0.67
    liest
    0.66
    osphere
    0.57
     matchup
    0.55
    hest
    0.54
     axis
    0.52
     element
    0.51
    cients
    0.51
     section
    0.50
    Act Density 0.914%

    No Known Activations