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

    Neuronpedia

    INDEX
    Explanations

    personal statements and conversations involving two people

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal feelings and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hels
    -0.72
    è¦ļéĨĴ
    -0.63
     looph
    -0.62
     resides
    -0.61
     Farming
    -0.60
    ospons
    -0.57
     Vendor
    -0.57
    ¥ŀ
    -0.56
     undertook
    -0.56
     resided
    -0.54
    POSITIVE LOGITS
    laughs
    0.90
    laugh
    0.82
     kinda
    0.72
     understand
    0.71
     tell
    0.71
     hug
    0.70
     laugh
    0.69
    Laughs
    0.68
     relate
    0.68
     feel
    0.67
    Act Density 0.436%

    No Known Activations