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

    Neuronpedia

    INDEX
    Explanations

    patterns related to numerical data and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opsis
    -0.15
    berman
    -0.15
    ense
    -0.15
     greeting
    -0.14
    ncoder
    -0.13
    .sponge
    -0.13
    ope
    -0.13
    ãĥıãĤ¤
    -0.13
    epad
    -0.13
    hol
    -0.12
    POSITIVE LOGITS
    ấn
    0.15
    ayscale
    0.14
    angel
    0.14
     angel
    0.14
    alled
    0.14
    ucha
    0.14
    ody
    0.14
    ddit
    0.14
    calar
    0.14
    /Framework
    0.13
    Act Density 0.493%

    No Known Activations