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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize means or methods of doing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ietf
    -0.17
    ÑģоÑĤ
    -0.17
    cky
    -0.16
    usz
    -0.15
    rapper
    -0.15
    allis
    -0.15
    tright
    -0.15
    uels
    -0.15
    ivor
    -0.14
    IER
    -0.14
    POSITIVE LOGITS
     station
    0.22
    fair
    0.21
     stations
    0.21
    finding
    0.20
     back
    0.20
    lon
    0.20
    ward
    0.20
    lay
    0.20
    far
    0.20
    esian
    0.18
    Act Density 0.024%

    No Known Activations