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

    Neuronpedia

    INDEX
    Explanations

    words related to political or social movements and gatherings

    oai_token-act-pair · gpt-3.5-turbo

    words related to gathering or mobilization activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abilities
    -0.92
    fiction
    -0.77
    agate
    -0.75
    etheless
    -0.75
    andro
    -0.71
    missions
    -0.65
    hid
    -0.65
    ungle
    -0.64
    leg
    -0.64
    percent
    -0.64
    POSITIVE LOGITS
     rallying
    0.94
    ãĤ¤ãĥĪ
    0.84
     rally
    0.81
     chorus
    0.78
     cries
    0.76
     GOODMAN
    0.74
    steen
    0.74
     cry
    0.72
     Rally
    0.71
    Spread
    0.70
    Act Density 0.008%

    No Known Activations