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

    Neuronpedia

    INDEX
    Explanations

    expressions related to awe and amazement

    oai_token-act-pair · gpt-3.5-turbo

    expressions of awe and appreciation for nature and the cosmos

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppo
    -0.87
    opter
    -0.79
    adic
    -0.75
    syn
    -0.72
    pered
    -0.72
    incarn
    -0.71
    middle
    -0.71
    existence
    -0.71
    closure
    -0.71
    itch
    -0.70
    POSITIVE LOGITS
     wonders
    1.33
     aloud
    0.94
     marvel
    0.85
     Wonders
    0.81
     heights
    0.78
     wonder
    0.72
     anew
    0.71
     miracles
    0.71
     mysteries
    0.69
     puzzles
    0.69
    Act Density 0.010%

    No Known Activations