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

    Neuronpedia

    INDEX
    Explanations

    the word "do" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stdexcept
    -0.15
    mtree
    -0.14
    обÑĭ
    -0.14
    ginas
    -0.14
    wij
    -0.14
    aby
    -0.14
     Milo
    -0.14
    umbn
    -0.14
    agon
    -0.14
     lẽ
    -0.14
    POSITIVE LOGITS
    zens
    0.19
    sel
    0.16
     correspondent
    0.15
    ivities
    0.15
     rem
    0.15
    jective
    0.14
    rent
    0.14
    zet
    0.14
     Toll
    0.14
    inger
    0.14
    Act Density 0.004%

    No Known Activations