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

    Neuronpedia

    INDEX
    Explanations

    fragmented sentences or incomplete thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    767
    -0.18
    AZY
    -0.17
    mada
    -0.17
    aira
    -0.16
    itia
    -0.16
     Norris
    -0.14
    scaled
    -0.14
    ",-
    -0.14
    ropol
    -0.14
    ubbo
    -0.14
    POSITIVE LOGITS
    Ĥæķ°
    0.15
     unlike
    0.15
     counting
    0.14
    wall
    0.14
     counted
    0.14
    org
    0.14
    dump
    0.13
     tim
    0.13
    ware
    0.13
     lives
    0.13
    Act Density 0.265%

    No Known Activations