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

    Neuronpedia

    INDEX
    Explanations

    phrases related to disgrace or shame

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of disgrace or being disgraced

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     needle
    -0.71
     blades
    -0.65
     Ju
    -0.65
     knife
    -0.63
     specialization
    -0.63
     picking
    -0.61
     knives
    -0.60
     du
    -0.60
     release
    -0.59
     amen
    -0.58
    POSITIVE LOGITS
    aced
    4.38
    aces
    2.30
    acing
    2.13
    ace
    1.68
    untled
    1.44
    acer
    1.35
    ACE
    1.32
    acements
    1.29
    acers
    1.21
    ittered
    1.17
    Act Density 0.005%

    No Known Activations