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

    Neuronpedia

    INDEX
    Explanations

    claims regarding social and political issues and their perceived impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mate
    -0.71
    Torrent
    -0.67
    gren
    -0.67
     Dynamo
    -0.65
    brother
    -0.64
    pleted
    -0.63
    hess
    -0.63
    IFE
    -0.63
     PLUS
    -0.63
    dies
    -0.63
    POSITIVE LOGITS
     simplistic
    1.20
     exagger
    1.11
     dismiss
    1.08
     caricature
    1.08
     blaming
    1.07
     dispar
    1.06
     dismissing
    1.04
     notions
    1.03
     overly
    1.03
     explanations
    1.02
    Act Density 0.310%

    No Known Activations