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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "so."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entic
    -0.15
    ÅĻÃŃž
    -0.15
    олож
    -0.14
    ubic
    -0.14
    elle
    -0.14
    ongs
    -0.14
    .yy
    -0.14
    Æ¡n
    -0.14
    beits
    -0.14
    usterity
    -0.13
    POSITIVE LOGITS
    vr
    0.17
    ãĥªãĥ¼ãĤº
    0.15
    amm
    0.15
     æ¾
    0.14
    ire
    0.14
    evi
    0.14
    BufferData
    0.14
    iyan
    0.14
    olio
    0.14
     grav
    0.13
    Act Density 0.008%

    No Known Activations