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

    Neuronpedia

    INDEX
    Explanations

    the word "normally."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ern
    -0.16
    uyu
    -0.15
    oter
    -0.14
    ContextHolder
    -0.14
    enant
    -0.14
    än
    -0.14
    &T
    -0.14
    iet
    -0.13
    ãĥĪãĥ«
    -0.13
     rap
    -0.13
    POSITIVE LOGITS
    ewood
    0.17
    ceph
    0.16
    preh
    0.15
    oreach
    0.14
    uper
    0.14
    opaque
    0.14
     Wooden
    0.14
    952
    0.13
    759
    0.13
    lef
    0.13
    Act Density 0.007%

    No Known Activations