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

    Neuronpedia

    INDEX
    Explanations

    verbs related to remaining in a specific state or position

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stay" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.71
    MRI
    -0.68
    NetMessage
    -0.68
    raid
    -0.67
    ologies
    -0.67
    HCR
    -0.66
    ocol
    -0.66
    toc
    -0.66
    DragonMagazine
    -0.65
     Proceed
    -0.65
    POSITIVE LOGITS
     afloat
    1.14
    cation
    1.07
     quiet
    0.94
     awake
    0.92
     alive
    0.92
     silent
    0.92
     calm
    0.91
     undefeated
    0.88
     away
    0.86
     awhile
    0.85
    Act Density 0.031%

    No Known Activations