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

    Neuronpedia

    INDEX
    Explanations

    terms related to visual perception and optical phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ‘
    -0.26
    ‘
    -0.25
     “
    -0.23
    âĢIJ
    -0.22
    âĢħ
    -0.22
     ’
    -0.22
    ’
    -0.21
    âĢ¯
    -0.21
    ’’
    -0.21
    ’S
    -0.20
    POSITIVE LOGITS
     blat
    0.15
     creds
    0.14
     acknow
    0.14
     pointers
    0.13
     emphasis
    0.13
     nods
    0.13
     clearly
    0.13
     indic
    0.12
     descriptors
    0.12
     porr
    0.12
    Act Density 0.118%

    No Known Activations