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

    Neuronpedia

    INDEX
    Explanations

    emotional responses and reactions to shocking or surprising experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rawDesc
    -0.63
     /\.(
    -0.62
    PreAuthorize
    -0.60
    ExtendWith
    -0.60
    arXiv
    -0.58
     Parcelable
    -0.58
     onCreate
    -0.57
    ⓧ
    -0.56
    -0.56
    SizeMode
    -0.54
    POSITIVE LOGITS
     shocked
    1.37
     astonished
    1.25
     surprised
    1.22
    shocked
    1.21
     amazed
    1.20
     amazement
    1.19
    surprised
    1.17
     astonishment
    1.14
     SHOCK
    1.12
    Surprised
    1.11
    Act Density 0.175%

    No Known Activations