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

    Neuronpedia

    INDEX
    Explanations

    numerical identifiers or designations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stad
    -0.18
    rieve
    -0.17
    laus
    -0.17
    à¹ĥà¸Ī
    -0.15
    elson
    -0.15
    äºĮäºĮ
    -0.15
    ем
    -0.14
    tega
    -0.14
    ког
    -0.14
    ../
    -0.14
    POSITIVE LOGITS
    nd
    0.31
    -thirds
    0.24
    nder
    0.20
     dozen
    0.20
    ï¸ı
    0.19
    ehir
    0.17
    gether
    0.16
    undry
    0.16
    gnore
    0.15
    ième
    0.15
    Act Density 0.466%

    No Known Activations