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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax elements or code structure endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĥãĥĪ
    -0.17
    itness
    -0.16
    ça
    -0.15
     archae
    -0.15
    ester
    -0.15
    tron
    -0.14
    Av
    -0.14
    lia
    -0.14
    rie
    -0.14
    .av
    -0.14
    POSITIVE LOGITS
    殿
    0.17
    oltip
    0.16
    ETS
    0.15
    GH
    0.15
     Glow
    0.15
    ξε
    0.14
    INCT
    0.14
    èŃ
    0.14
    herits
    0.14
    anuts
    0.14
    Act Density 0.002%

    No Known Activations