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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "been" and variations of 'to be' that imply past experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ł
    -0.16
    vé
    -0.15
    810
    -0.15
    ese
    -0.14
    .Fetch
    -0.14
    jej
    -0.14
    ons
    -0.13
     mat
    -0.13
    arious
    -0.13
    /net
    -0.13
    POSITIVE LOGITS
    agers
    0.16
    dum
    0.15
    Arena
    0.15
     ArgumentError
    0.14
    ergy
    0.14
     Äijẳng
    0.14
    greso
    0.14
    327
    0.14
    ny
    0.14
     vip
    0.14
    Act Density 0.187%

    No Known Activations