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

    Neuronpedia

    INDEX
    Explanations

    words associated with extremes or significant characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hue
    -0.15
    mouseenter
    -0.14
     LSB
    -0.14
    mez
    -0.14
    PTS
    -0.14
     Matth
    -0.13
    dration
    -0.13
    mium
    -0.13
    оÑĢÑıд
    -0.13
    ÄĽr
    -0.13
    POSITIVE LOGITS
    st
    0.79
    est
    0.68
    ste
    0.52
    ests
    0.52
    sten
    0.50
    sts
    0.50
    ster
    0.49
    EST
    0.48
    sti
    0.48
    ast
    0.47
    Act Density 0.143%

    No Known Activations