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

    Neuronpedia

    INDEX
    Explanations

    expressions of astonishment or disbelief

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing disbelief or frustration towards actions or decisions made by authorities or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amental
    -0.59
     Basics
    -0.59
     Cure
    -0.57
     VID
    -0.57
     Proof
    -0.55
     gist
    -0.54
     TRUE
    -0.53
     bye
    -0.53
    igate
    -0.52
    tnc
    -0.52
    POSITIVE LOGITS
     bothered
    1.15
     hadn
    1.03
     didnt
    1.01
     dared
    0.96
     chose
    0.93
     bothers
    0.93
     would
    0.93
     bother
    0.92
     wouldn
    0.90
     couldn
    0.90
    Act Density 0.266%

    No Known Activations