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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news headlines or events

    oai_token-act-pair · gpt-3.5-turbo

    colons and the associated content in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stellar
    -0.73
    orb
    -0.70
    uga
    -0.70
    mone
    -0.70
    XXX
    -0.69
    NetMessage
    -0.68
    ozo
    -0.68
    halla
    -0.67
     consolid
    -0.66
    itol
    -0.66
    POSITIVE LOGITS
     Protesters
    1.09
     Despite
    1.04
     Thousands
    1.04
     Former
    1.02
     Scenes
    1.01
     Photograph
    0.98
     Hundreds
    0.97
     An
    0.95
     Researchers
    0.94
     Supporters
    0.94
    Act Density 0.072%

    No Known Activations