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

    Neuronpedia

    INDEX
    Explanations

    positional or directional terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    597
    -0.20
    unn
    -0.17
    elsen
    -0.17
    598
    -0.16
    abar
    -0.15
    ä
    -0.14
    578
    -0.14
    εÏģÏĮ
    -0.14
    EX
    -0.14
    èĪĪ
    -0.14
    POSITIVE LOGITS
     alike
    0.15
    mmo
    0.14
    opal
    0.14
    affles
    0.14
    ITO
    0.14
    astery
    0.14
    .CreateInstance
    0.13
    Guy
    0.13
    abyrin
    0.13
     Guy
    0.13
    Act Density 0.138%

    No Known Activations