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

    Neuronpedia

    INDEX
    Explanations

    phrases related to public engagement and societal matters

    oai_token-act-pair · gpt-3.5-turbo

    references to public engagement and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Pacific
    -0.72
     Valhalla
    -0.67
    akuya
    -0.66
    inally
    -0.66
    akov
    -0.64
     thrott
    -0.64
     Yamato
    -0.64
    zyme
    -0.64
    rett
    -0.63
    rontal
    -0.62
    POSITIVE LOGITS
     opinion
    0.91
    atures
    0.72
     bond
    0.71
     ORDER
    0.66
    erences
    0.66
     oath
    0.65
     alike
    0.64
     antioxid
    0.62
     sworn
    0.62
     opinions
    0.62
    Act Density 0.187%

    No Known Activations