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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting related to numerical data or dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olini
    -0.15
    912
    -0.15
    Äĥng
    -0.15
    lege
    -0.14
    ULSE
    -0.14
     Rede
    -0.14
    VELO
    -0.13
    vert
    -0.13
    rollers
    -0.13
     DISCLAIMER
    -0.13
    POSITIVE LOGITS
    ville
    0.20
    ãĤ
    0.16
    .sponge
    0.16
     Buckley
    0.15
    erville
    0.14
    inkel
    0.14
    VILLE
    0.14
    ischer
    0.14
    atron
    0.13
    Disappear
    0.13
    Act Density 0.284%

    No Known Activations