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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and numeric values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /repository
    -0.15
    .gstatic
    -0.15
    ase
    -0.15
     Bret
    -0.15
    212
    -0.15
    acher
    -0.14
    dera
    -0.14
    ruž
    -0.14
    ponsible
    -0.14
    vertising
    -0.13
    POSITIVE LOGITS
     Amen
    0.17
    venes
    0.15
    omba
    0.14
    assin
    0.14
    Opts
    0.14
    apos
    0.14
     consecutive
    0.14
    etre
    0.13
    ansom
    0.13
     sanitation
    0.13
    Act Density 0.044%

    No Known Activations