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

    Neuronpedia

    INDEX
    Explanations

    key verbs and adjectives, particularly those that indicate a strong opinion or evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auen
    -0.18
     sobie
    -0.15
     ÙĨÙĤد
    -0.14
    uby
    -0.14
    OKIE
    -0.14
    ulg
    -0.14
    æī¹
    -0.14
     //!<
    -0.13
    inke
    -0.13
    immutable
    -0.13
    POSITIVE LOGITS
     similarly
    0.17
     cạnh
    0.17
     specifically
    0.16
     upgrade
    0.16
    Specific
    0.16
    ãĥ³ãĥĸ
    0.15
     specific
    0.15
     similar
    0.15
     equally
    0.15
    utherford
    0.15
    Act Density 0.007%

    No Known Activations