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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal conditions and approvals for software distribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.87
     himſelf
    -0.82
     themſelves
    -0.78
     itſelf
    -0.77
     Efq
    -0.77
     Theſe
    -0.74
    LabelTagHelper
    -0.71
     pleaſure
    -0.69
     ſeveral
    -0.69
     Anſ
    -0.68
    POSITIVE LOGITS
     but
    0.53
     However
    0.50
    but
    0.50
    Note
    0.50
    However
    0.49
     albeit
    0.47
    ただし
    0.47
    但我
    0.47
     BUT
    0.47
     但是
    0.47
    Act Density 0.328%

    No Known Activations