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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal experiences and emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chriſt
    -1.08
     Monfieur
    -1.01
     Chriftian
    -0.92
     purpoſe
    -0.90
     ſeveral
    -0.90
     houſe
    -0.88
     Perſ
    -0.87
     greateſt
    -0.86
    ImageContext
    -0.86
     Diſ
    -0.85
    POSITIVE LOGITS
     let
    0.70
     be
    0.67
     F
    0.66
     Me
    0.66
     נ
    0.65
     he
    0.64
     se
    0.63
     have
    0.63
     Ha
    0.61
     j
    0.61
    Act Density 0.047%

    No Known Activations