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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize relationships and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.76
    rungsseite
    -0.61
     And
    -0.55
    дарт
    -0.52
     resourceCulture
    -0.51
    And
    -0.50
    colage
    -0.48
    :✨
    -0.47
    ation
    -0.45
    l
    -0.45
    POSITIVE LOGITS
     itſelf
    0.92
     Efq
    0.83
    GHIJKLM
    0.81
     ſever
    0.81
     Monfieur
    0.78
     Jefus
    0.77
    ſelf
    0.77
    NewUrlParser
    0.76
     myſelf
    0.76
     pleaſure
    0.76
    Act Density 0.455%

    No Known Activations