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

    Neuronpedia

    INDEX
    Explanations

    descriptions of simplicity or ease in tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipy
    -0.16
    ERV
    -0.15
    ibt
    -0.15
    sett
    -0.15
    tape
    -0.15
    GY
    -0.14
     longer
    -0.14
    nge
    -0.14
     equ
    -0.14
    arga
    -0.14
    POSITIVE LOGITS
    /free
    0.18
     easy
    0.17
    uez
    0.16
    aylor
    0.16
     dÃłng
    0.16
    iez
    0.15
    olian
    0.15
    عا
    0.15
    /simple
    0.15
    easy
    0.15
    Act Density 0.084%

    No Known Activations