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

    Neuronpedia

    INDEX
    Explanations

    references to the name "David."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stdc
    -0.51
    таратура
    -0.44
    :✨
    -0.43
     ſta
    -0.41
     bordado
    -0.41
     setw
    -0.40
     juſ
    -0.40
     čet
    -0.40
     paſſ
    -0.39
    Captor
    -0.39
    POSITIVE LOGITS
    thing
    0.66
    thin
    0.63
     sometimes
    0.63
    Thin
    0.61
     Thin
    0.60
     Thing
    0.60
    Thing
    0.56
    sometimes
    0.56
     thin
    0.55
    Sometimes
    0.54
    Act Density 0.172%

    No Known Activations