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

    Neuronpedia

    INDEX
    Explanations

    references to historical or cultural elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Schwarz
    -0.14
    æ¢ģ
    -0.14
    çIJĥ
    -0.14
    âĶģ
    -0.14
    ÎŃν
    -0.13
     Walk
    -0.13
    lob
    -0.13
    oping
    -0.13
     Earn
    -0.13
    essim
    -0.13
    POSITIVE LOGITS
     characters
    0.34
     writing
    0.32
     syll
    0.27
     Characters
    0.27
     scripts
    0.26
     Writing
    0.26
     ide
    0.26
    characters
    0.25
     orth
    0.25
    Writing
    0.25
    Act Density 0.046%

    No Known Activations