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

    Neuronpedia

    INDEX
    Explanations

    phrases related to authority figures or formal organizations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to governance and media influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eternity
    -0.55
    ãĤ¯
    -0.54
     Brow
    -0.53
    taining
    -0.52
    fitting
    -0.51
    font
    -0.50
    ipedia
    -0.48
    etime
    -0.48
    zac
    -0.45
    tnc
    -0.45
    POSITIVE LOGITS
     reacted
    0.85
     succeeded
    0.80
     took
    0.79
     went
    0.78
     had
    0.78
     gave
    0.77
     did
    0.75
     has
    0.75
     threw
    0.74
     recognizes
    0.74
    Act Density 0.954%

    No Known Activations