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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Then" used to introduce or transition between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.77
     himſelf
    -0.76
     themſelves
    -0.75
     GenerationType
    -0.71
    randomUUID
    -0.71
    ilíbrio
    -0.70
     Irm
    -0.69
     Guggenheim
    -0.69
     Ophelia
    -0.69
     Majefty
    -0.68
    POSITIVE LOGITS
     THEN
    0.68
    emons
    0.67
    clearly
    0.65
    vdash
    0.64
    THEN
    0.64
     maybe
    0.64
     perhaps
    0.61
    cinta
    0.61
    สิน
    0.61
    れたら
    0.60
    Act Density 0.105%

    No Known Activations