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

    Neuronpedia

    INDEX
    Explanations

    phrases related to quotations or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    [".
    -0.15
    äºĭæĥħ
    -0.15
    Ñģли
    -0.15
    ãĥ³ãĤ¿
    -0.14
    ’ta
    -0.14
     CASCADE
    -0.14
    ablish
    -0.14
    ssize
    -0.14
    amam
    -0.14
    upy
    -0.14
    POSITIVE LOGITS
    /'
    0.30
     '
    0.28
    -'
    0.25
     '[
    0.24
     ('
    0.24
     ‘
    0.22
    ...'
    0.21
    ãĢģãĢİ
    0.20
    =='
    0.20
     '*
    0.19
    Act Density 0.154%

    No Known Activations