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

    Neuronpedia

    INDEX
    Explanations

    locations or events related to political protests

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or sites related to political activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    states
    -0.87
     Nationwide
    -0.74
    raft
    -0.69
    erm
    -0.66
    model
    -0.66
    Users
    -0.63
    orem
    -0.63
     TBD
    -0.62
    state
    -0.61
     Survivor
    -0.61
    POSITIVE LOGITS
    rir
    1.16
    ascus
    1.00
    ée
    0.88
    unda
    0.84
     rall
    0.84
    unta
    0.82
    adish
    0.82
    antes
    0.80
    ashtra
    0.79
    andom
    0.78
    Act Density 0.011%

    No Known Activations