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

    Neuronpedia

    INDEX
    Explanations

    formatted data structures and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (
    -0.68
    <eos>
    -0.58
    and
    -0.55
    (
    -0.54
     The
    -0.54
    de
    -0.53
    ”
    -0.53
    C
    -0.52
     “
    -0.51
     and
    -0.51
    POSITIVE LOGITS
     pleaſure
    1.03
     myſelf
    0.91
     ſmall
    0.90
     Jefus
    0.89
     greateſt
    0.88
     MainAxisSize
    0.88
    enumi
    0.86
     Diſ
    0.86
     purpoſe
    0.86
     Majefty
    0.84
    Act Density 0.374%

    No Known Activations