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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "out."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    {{{
    -0.15
    /memory
    -0.15
    halt
    -0.14
    headed
    -0.14
    bast
    -0.14
    embers
    -0.14
    bsite
    -0.14
    odor
    -0.14
     ground
    -0.13
    plex
    -0.13
    POSITIVE LOGITS
    flows
    0.15
     Ä°z
    0.15
    ucene
    0.15
    adel
    0.14
     Haz
    0.14
    erli
    0.14
    flow
    0.14
    appen
    0.14
    comes
    0.13
    teg
    0.13
    Act Density 0.083%

    No Known Activations