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

    Neuronpedia

    INDEX
    Explanations

    various forms of punctuation or dashes in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.77
    :
    -0.56
     etc
    -0.55
    ,....
    -0.50
    ......
    -0.48
    .
    -0.47
    ...."
    -0.46
    ...")
    -0.46
    ・・・」
    -0.46
    、、、
    -0.46
    POSITIVE LOGITS
    –
    0.98
    ----------------
    0.84
     это
    0.77
    ––––
    0.77
    especially
    0.76
    namely
    0.76
    – 
    0.75
    including
    0.73
    except
    0.73
    even
    0.71
    Act Density 0.341%

    No Known Activations