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

    Neuronpedia

    INDEX
    Explanations

    words related to anti-government activities or movements

    oai_token-act-pair · gpt-3.5-turbo

    references to anti- policies or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     srfAttach
    -0.71
    staking
    -0.66
     dots
    -0.64
     snug
    -0.63
     notebooks
    -0.63
     belts
    -0.60
    LESS
    -0.59
    natureconservancy
    -0.59
    channelAvailability
    -0.58
     valiant
    -0.57
    POSITIVE LOGITS
    akable
    0.82
    usterity
    0.80
    otic
    0.80
    ritic
    0.79
    amation
    0.78
    roleum
    0.77
    errilla
    0.77
    closure
    0.77
    anto
    0.77
    amacare
    0.76
    Act Density 0.101%

    No Known Activations