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

    Neuronpedia

    INDEX
    Explanations

    emotional language related to personal feelings and beliefs

    oai_token-act-pair · gpt-3.5-turbo

    references to emotional expressions and existential themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     peacefully
    -0.61
    online
    -0.59
    arthed
    -0.58
    NOW
    -0.58
    appropriately
    -0.58
    Together
    -0.57
    together
    -0.56
    anwhile
    -0.56
    edIn
    -0.56
    aughs
    -0.54
    POSITIVE LOGITS
     toward
    0.77
     to
    0.77
     towards
    0.75
     guiName
    0.63
    to
    0.63
     for
    0.62
    )=(
    0.61
    âĢ
    0.60
     whereby
    0.58
     âĢ
    0.58
    Act Density 0.981%

    No Known Activations