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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to specific situations or instances

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate common situations or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeus
    -0.87
    shaw
    -0.80
    culosis
    -0.71
    arnaev
    -0.70
    matter
    -0.68
    kamp
    -0.67
    endor
    -0.67
    onis
    -0.66
    Rated
    -0.65
    strength
    -0.64
    POSITIVE LOGITS
     occasions
    1.06
     rare
    1.05
     situations
    1.04
     moments
    0.91
     things
    0.91
     pesky
    0.89
     cases
    0.88
     annoying
    0.84
     weird
    0.80
     acron
    0.79
    Act Density 0.073%

    No Known Activations