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

    Neuronpedia

    INDEX
    Explanations

    sentence fragments with non-alphanumeric characters

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations or entities involved in medical or regulatory contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dehyd
    -0.72
     Barber
    -0.67
     pacif
    -0.67
     bomb
    -0.65
     Sgt
    -0.64
     Shinra
    -0.63
     grop
    -0.63
     unconditional
    -0.60
     scrap
    -0.60
     jailed
    -0.60
    POSITIVE LOGITS
    Contents
    0.98
    NAS
    0.96
    Guest
    0.96
    pmwiki
    0.94
    Document
    0.91
    ccording
    0.91
    Enlarge
    0.91
    Ear
    0.90
    Updated
    0.90
    Introduction
    0.90
    Act Density 0.269%

    No Known Activations