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

    Neuronpedia

    INDEX
    Explanations

    occurrences of words beginning with the letter 'e'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    d
    -0.83
    v
    -0.69
    k
    -0.69
    n
    -0.68
    t
    -0.65
    st
    -0.62
    f
    -0.61
    ll
    -0.58
    m
    -0.58
    z
    -0.57
    POSITIVE LOGITS
    ureka
    0.48
    ponym
    0.47
    oe
    0.47
    chos
    0.47
     prácti
    0.46
    argout
    0.45
    an
    0.45
    lips
    0.45
    oa
    0.44
    al
    0.44
    Act Density 0.212%

    No Known Activations