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

    Neuronpedia

    INDEX
    Explanations

    key concepts related to time and progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elsing
    -0.16
    zion
    -0.15
    agini
    -0.15
    atrix
    -0.14
     Bog
    -0.14
    ehen
    -0.14
    odos
    -0.14
    ãĥĨãĥ«
    -0.13
    orre
    -0.13
     Gross
    -0.13
    POSITIVE LOGITS
    票
    0.15
     reserve
    0.15
     eiusmod
    0.15
     tÆ°
    0.15
    oned
    0.15
    olk
    0.15
     Sunder
    0.14
    292
    0.14
    annes
    0.14
    allen
    0.14
    Act Density 0.317%

    No Known Activations