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

    Neuronpedia

    INDEX
    Explanations

    emotional responses and reactions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     livest
    -0.67
    amins
    -0.65
    Ranked
    -0.65
    tein
    -0.64
    amation
    -0.61
     landfill
    -0.61
     wiki
    -0.59
    lay
    -0.59
    ublic
    -0.58
    ictionary
    -0.58
    POSITIVE LOGITS
    ingly
    1.04
     ABOUT
    0.84
     about
    0.81
    NESS
    0.76
    wart
    0.75
    whel
    0.73
    der
    0.73
    dy
    0.71
    lessly
    0.70
    fully
    0.70
    Act Density 3.813%

    No Known Activations