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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "op" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    y
    -0.38
    h
    -0.27
    t
    -0.27
    s
    -0.26
    er
    -0.26
    ic
    -0.25
    e
    -0.25
    yb
    -0.24
    eurs
    -0.20
    yar
    -0.20
    POSITIVE LOGITS
    posite
    0.22
    edia
    0.22
    ausal
    0.22
    portunity
    0.21
    lastic
    0.19
    las
    0.19
    ercul
    0.18
    inion
    0.18
    pi
    0.18
    corn
    0.18
    Act Density 0.020%

    No Known Activations