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

    Neuronpedia

    INDEX
    Explanations

    references to team memberships and organizational affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     plus
    -0.17
     throughout
    -0.15
    amar
    -0.15
     everywhere
    -0.15
     Throughout
    -0.14
    osh
    -0.14
    itur
    -0.14
    ãĤ¤ãĥ«
    -0.14
    Throughout
    -0.14
    contained
    -0.13
    POSITIVE LOGITS
     full
    0.31
    -full
    0.24
     permanent
    0.24
     permanently
    0.24
    full
    0.24
    .full
    0.23
     ranks
    0.22
     Full
    0.22
     fold
    0.22
    (full
    0.22
    Act Density 0.080%

    No Known Activations