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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÅĽci
    -0.17
     Hers
    -0.15
    ủng
    -0.15
    ssel
    -0.15
    orf
    -0.14
    idden
    -0.14
    LAS
    -0.14
     Cleveland
    -0.14
    .cl
    -0.14
    ihar
    -0.14
    POSITIVE LOGITS
    ãĥ³ãĥĨ
    0.16
    entina
    0.16
    º
    0.15
    å¹ķ
    0.15
    ara
    0.15
    zet
    0.14
    lok
    0.14
    497
    0.14
    μÎŃνα
    0.14
    ±Ð¾ÑĤ
    0.14
    Act Density 0.004%

    No Known Activations