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

    Neuronpedia

    INDEX
    Explanations

    punctuations and expressions indicating questions, exclamations, or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     niestety
    -0.54
    実は
    -0.53
     MainAxisSize
    -0.51
     interestingly
    -0.49
     unfortunately
    -0.47
    __':
    -0.44
    TextWatcher
    -0.44
     Unfortunately
    -0.44
    AddTagHelper
    -0.44
    嘿嘿
    -0.44
    POSITIVE LOGITS
     seriously
    1.35
    seriously
    1.29
    Seriously
    1.27
     Seriously
    1.21
     wtf
    1.02
     WTF
    1.01
    WTF
    0.98
     Wtf
    0.92
     dude
    0.89
    Wtf
    0.86
    Act Density 0.257%

    No Known Activations