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

    Neuronpedia

    INDEX
    Explanations

    the word "initial" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ess
    -0.18
    esh
    -0.18
    774
    -0.16
    iid
    -0.16
    oi
    -0.15
    ijk
    -0.14
    eka
    -0.14
    ese
    -0.14
    au
    -0.14
    aceous
    -0.14
    POSITIVE LOGITS
    mente
    0.25
    /original
    0.23
    aneously
    0.23
    dehyde
    0.18
    ë¶ĢíĦ°
    0.18
    ities
    0.18
    ised
    0.17
    iltr
    0.17
    arily
    0.17
    (initial
    0.16
    Act Density 0.012%

    No Known Activations