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

    Neuronpedia

    INDEX
    Explanations

    sequences of characters that resemble formatting, such as parentheses and dashes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    500
    -0.16
    969
    -0.15
    lease
    -0.15
    636
    -0.15
    248
    -0.14
     property
    -0.14
    553
    -0.14
    536
    -0.14
    742
    -0.14
    hte
    -0.14
    POSITIVE LOGITS
    èĶµ
    0.17
    imb
    0.15
    IBE
    0.14
    BBBB
    0.14
    bern
    0.14
    Accessor
    0.14
    ì°
    0.14
    decorate
    0.14
    .instructions
    0.14
    ovna
    0.14
    Act Density 0.021%

    No Known Activations