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

    Neuronpedia

    INDEX
    Explanations

    the start of a new section or significant content within the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.59
     "
    -0.58
     Hau
    -0.55
     #
    -0.55
     si
    -0.55
    <eos>
    -0.55
     around
    -0.52
    ers
    -0.52
     phá
    -0.51
    ので
    -0.50
    POSITIVE LOGITS
    enumi
    1.49
    \{\\
    1.31
     BoxDecoration
    1.27
     للمعارف
    1.22
    +#+#
    1.21
    !*\
    1.19
    tvguidetime
    1.19
    enumii
    1.18
    ]")]
    1.17
     MainAxisSize
    1.16
    Act Density 0.034%

    No Known Activations