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

    Neuronpedia

    INDEX
    Explanations

    connections to temporal phrases and indicators of organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilet
    -0.17
    ayo
    -0.16
    ugi
    -0.14
    Ïįν
    -0.13
    еÑĢÑĸ
    -0.13
     marrow
    -0.13
    ensation
    -0.13
    _OW
    -0.13
    usercontent
    -0.13
    lec
    -0.13
    POSITIVE LOGITS
    ãĥ³ãĥī
    0.16
    UnderTest
    0.15
     ordin
    0.15
    rahim
    0.15
    873
    0.14
    ylko
    0.14
    strap
    0.14
    dbl
    0.14
     Blasio
    0.14
    OTE
    0.13
    Act Density 0.004%

    No Known Activations