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

    Neuronpedia

    INDEX
    Explanations

    verbs related to the action of remaining or maintaining a certain state or position

    oai_token-act-pair · gpt-3.5-turbo

    expressions and references to the word "stay."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olan
    -0.77
    =>
    -0.72
    asking
    -0.70
    osion
    -0.70
    ORS
    -0.68
     congratulations
    -0.65
    stadt
    -0.65
    rely
    -0.64
    rette
    -0.64
    isson
    -0.63
    POSITIVE LOGITS
     afloat
    1.23
     sane
    1.13
     alive
    1.05
     disciplined
    1.00
     calm
    1.00
     relevant
    0.99
     grounded
    0.97
     classy
    0.97
     awake
    0.96
     solvent
    0.96
    Act Density 0.080%

    No Known Activations