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

    Neuronpedia

    INDEX
    Explanations

    terms related to short-term strategies or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to short-term concepts or timeframes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ADRA
    -0.77
     Ukrain
    -0.67
    iance
    -0.66
     wreck
    -0.63
     Monarch
    -0.62
     vou
    -0.60
     Remastered
    -0.60
     Democr
    -0.60
     Braz
    -0.60
    apon
    -0.59
    POSITIVE LOGITS
    lived
    1.31
    sighted
    1.25
    term
    1.20
    comings
    1.17
    circ
    1.10
    sized
    1.02
    Term
    1.01
    handed
    1.00
    notice
    0.99
    duration
    0.98
    Act Density 0.041%

    No Known Activations