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

    Neuronpedia

    INDEX
    Explanations

    the frequency of the letter 'e' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eci
    -0.17
    UNUSED
    -0.16
    xdc
    -0.15
    angstrom
    -0.15
     stripslashes
    -0.14
    cgi
    -0.14
    IIIK
    -0.14
    eea
    -0.14
    ASSERT
    -0.14
    ³
    -0.14
    POSITIVE LOGITS
    .g
    0.47
     e
    0.39
     g
    0.38
    ,g
    0.30
    :g
    0.28
    g
    0.25
    e
    0.25
    (g
    0.24
    .e
    0.24
    	g
    0.22
    Act Density 0.011%

    No Known Activations