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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue or speech in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     {{↵
    -0.15
     '..
    -0.15
    ''↵
    -0.14
    athan
    -0.14
    ¾
    -0.14
    era
    -0.14
     Tit
    -0.14
     ÙĦÙĥ
    -0.14
    ''.
    -0.14
    &C
    -0.13
    POSITIVE LOGITS
    :
    0.40
    ा:
    0.22
    à¹Į:
    0.21
    :',↵
    0.20
    :↵
    0.19
    :")
    0.18
    :,
    0.18
    ,↵
    0.18
    :",↵
    0.17
    ,↵↵
    0.17
    Act Density 0.296%

    No Known Activations