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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks used in separating or concluding clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     iſt
    -1.13
     ―――――
    -0.90
    ReusableCell
    -0.84
    دانشنامهٔ
    -0.83
    BibitemShut
    -0.81
     يتيمه
    -0.80
     ་་
    -0.79
     XNUMX
    -0.79
    ſelves
    -0.78
     Anſ
    -0.76
    POSITIVE LOGITS
    ;
    1.02
    ;
    0.79
    ;">
    0.78
    );
    0.74
    .;
    0.74
    ;\
    0.72
    œ
    0.71
     ;
    0.69
     @"";
    0.68
    !;
    0.68
    Act Density 0.045%

    No Known Activations