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

    Neuronpedia

    INDEX
    Explanations

    friendly and affectionate messages

    oai_token-act-pair · gpt-3.5-turbo

    expressions of affection and well-wishing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     documentaries
    -0.67
     laughable
    -0.66
     hybrids
    -0.66
     remote
    -0.65
     vault
    -0.65
     hybrid
    -0.60
     lesser
    -0.60
     realised
    -0.59
     underest
    -0.59
     subt
    -0.58
    POSITIVE LOGITS
    Peace
    0.90
     amen
    0.88
    âĻ¥
    0.86
    eric
    0.85
     ______
    0.85
     Helpful
    0.84
    rely
    0.81
    ################################
    0.81
    ________________________
    0.81
    ________________________________________________________________
    0.80
    Act Density 0.323%

    No Known Activations