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

    Neuronpedia

    INDEX
    Explanations

    pairs of braces or brackets typically used in programming and mathematics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    an
    -1.15
    <i>
    -1.02
    <b>
    -0.99
    n
    -0.95
    r
    -0.95
    le
    -0.95
    a
    -0.94
    in
    -0.93
    l
    -0.89
    de
    -0.87
    POSITIVE LOGITS
    ("{}
    1.31
     للمعارف
    1.28
     purpoſe
    1.25
    :{}
    1.24
     theſe
    1.21
     myſelf
    1.19
    ^(@)
    1.18
     ainfi
    1.18
    !("{}",
    1.15
     themſelves
    1.13
    Act Density 0.339%

    No Known Activations