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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ease or simplicity in actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nite
    -0.17
    rani
    -0.16
     blank
    -0.16
    nement
    -0.16
    hta
    -0.15
     Bottom
    -0.14
     bottom
    -0.14
    unga
    -0.14
    .Bottom
    -0.14
    dech
    -0.14
    POSITIVE LOGITS
     dÃłng
    0.22
     Easily
    0.20
    ause
    0.18
     easily
    0.17
     Gst
    0.17
    Äħd
    0.15
    .setViewport
    0.15
    azon
    0.15
    .nb
    0.14
    514
    0.14
    Act Density 0.086%

    No Known Activations