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

    Neuronpedia

    INDEX
    Explanations

    numerical values or statistics within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ellan
    -0.16
    ele
    -0.16
    ilan
    -0.15
    ron
    -0.15
    urve
    -0.15
     Downing
    -0.15
    erland
    -0.14
    ignon
    -0.14
    mi
    -0.14
    dam
    -0.14
    POSITIVE LOGITS
     Birch
    0.16
    cente
    0.16
    laps
    0.15
    udo
    0.14
    lys
    0.14
    .hardware
    0.14
    stral
    0.14
    PRS
    0.13
    cue
    0.13
    .gs
    0.13
    Act Density 0.030%

    No Known Activations