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

    Neuronpedia

    INDEX
    Explanations

    HTML links and elements related to participants in a study

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Biôgrafia
    -0.88
    principalColumn
    -0.85
    . 
    -0.81
    нгред
    -0.76
     –>
    -0.75
    .'”
    -0.73
     GenerationType
    -0.73
    .’”
    -0.72
    astéroïdes
    -0.71
    …]
    -0.71
    POSITIVE LOGITS
     ``
    1.02
    ``
    0.90
     „
    0.88
     «
    0.83
    「
    0.81
     `
    0.76
     ''
    0.69
    «
    0.65
    „
    0.65
    ｢
    0.65
    Act Density 1.793%

    No Known Activations