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

    Neuronpedia

    INDEX
    Explanations

    mathematical proofs and logical deductions in formal writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.98
     themſelves
    -0.91
     myſelf
    -0.90
     neceff
    -0.84
     occaf
    -0.84
     pinulongan
    -0.83
     Theſe
    -0.82
    TagMode
    -0.82
     ―――――
    -0.81
     photolibrary
    -0.81
    POSITIVE LOGITS
    НИК
    0.51
     
    0.50
    ↵↵
    0.49
     on
    0.49
     is
    0.49
     go
    0.48
     as
    0.48
     and
    0.47
     for
    0.47
     in
    0.45
    Act Density 3.158%

    No Known Activations