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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating preparation or planning for future actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raz
    -0.18
    ãĥĵãĥ¼
    -0.16
    rado
    -0.15
    asca
    -0.14
    ado
    -0.14
    çı
    -0.13
    intr
    -0.13
    urovision
    -0.13
    ermann
    -0.13
    493
    -0.13
    POSITIVE LOGITS
    (DialogInterface
    0.16
     Harding
    0.14
    rete
    0.14
    osh
    0.13
    LOB
    0.13
    ä¸įåĪ°
    0.13
     tú
    0.13
    vert
    0.13
    lew
    0.13
    .scalablytyped
    0.12
    Act Density 0.569%

    No Known Activations