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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the letter 'a' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    v
    -0.28
    j
    -0.27
    li
    -0.26
    le
    -0.26
    ct
    -0.25
    th
    -0.25
    z
    -0.25
    st
    -0.23
    la
    -0.23
    g
    -0.23
    POSITIVE LOGITS
     href
    0.22
    finity
    0.22
    éro
    0.21
    eron
    0.21
    akash
    0.21
    equip
    0.20
    equal
    0.20
    equ
    0.20
    arhus
    0.20
     posterior
    0.19
    Act Density 0.226%

    No Known Activations