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

    Neuronpedia

    INDEX
    Explanations

    phrases related to bringing positive emotions, especially related to making people smile

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing emotional responses and human connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ourced
    -0.85
    arella
    -0.78
    ADA
    -0.76
    adata
    -0.76
    cott
    -0.73
    reciation
    -0.71
    aza
    -0.71
    ptives
    -0.70
    ourcing
    -0.70
    wcs
    -0.70
    POSITIVE LOGITS
     darkest
    0.96
     otherwise
    0.94
     madness
    0.90
     psyche
    0.88
     turbulent
    0.88
     dismal
    0.85
     sleepy
    0.84
     mundane
    0.84
     proceedings
    0.83
     festive
    0.83
    Act Density 0.655%

    No Known Activations