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

    Neuronpedia

    INDEX
    Explanations

    repetitive or structured patterns in text, particularly focused on delimiters and quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    featureID
    -0.88
    Šaltiniai
    -0.77
    Ecotoxicity
    -0.74
     nakalista
    -0.71
    extAlignment
    -0.70
    basicConfig
    -0.68
     ExecuteAsync
    -0.68
    bkz
    -0.67
     getRule
    -0.65
     RestTemplate
    -0.65
    POSITIVE LOGITS
    hyrchwyd
    0.57
     pascal
    0.55
     combined
    0.53
     pleaſure
    0.52
    {"
    0.51
     cauſe
    0.51
    ziel
    0.49
     houſe
    0.49
     Hickman
    0.48
    {|
    0.48
    Act Density 0.100%

    No Known Activations