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

    Neuronpedia

    INDEX
    Explanations

    various forms of punctuation and quotation marks indicating dialogue or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -0.76
     „
    -0.73
    =”
    -0.63
    StrictEqual
    -0.58
     「
    -0.55
    opress
    -0.54
    __*/
    -0.53
     Beschluss
    -0.53
    washingtonpost
    -0.53
     createStore
    -0.52
    POSITIVE LOGITS
    ########.
    0.82
     Clapton
    0.74
    
    0.69
     فريبيس
    0.68
     Meadow
    0.68
    ChildScrollView
    0.68
     виправивши
    0.66
     TextInputType
    0.65
     Perci
    0.65
     Scotty
    0.65
    Act Density 0.113%

    No Known Activations