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

    Neuronpedia

    INDEX
    Explanations

    words related to the propagation or dissemination of information or ideas

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the spreading or dissemination of information, particularly misinformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heed
    -0.68
    staking
    -0.66
    auna
    -0.64
     compensation
    -0.64
    ney
    -0.64
    venge
    -0.63
    --+
    -0.63
     Picard
    -0.61
     Mile
    -0.60
     Pebble
    -0.59
    POSITIVE LOGITS
     tremend
    0.93
     propag
    0.85
    atform
    0.85
     pedd
    0.84
     dissemin
    0.84
    outing
    0.83
     disinformation
    0.80
     propagate
    0.80
    ong
    0.79
    ulations
    0.77
    Act Density 0.044%

    No Known Activations