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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political and social interactions

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases that connect entities or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bey
    -0.69
    YC
    -0.62
    Pink
    -0.62
    KEN
    -0.60
    Äį
    -0.56
    Lay
    -0.56
    Reloaded
    -0.54
    Ore
    -0.54
    RGB
    -0.53
    HK
    -0.53
    POSITIVE LOGITS
     races
    0.57
     spectator
    0.56
     agencies
    0.56
     Accountability
    0.53
     demographics
    0.53
     relations
    0.52
     Fram
    0.52
    blogs
    0.51
     perceptions
    0.51
     tools
    0.51
    Act Density 0.647%

    No Known Activations