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

    Neuronpedia

    INDEX
    Explanations

    tokens that indicate special formatting or markers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jalá
    -0.66
     becauſe
    -0.56
     Eſ
    -0.54
     inexp
    -0.53
     iſt
    -0.53
     enormously
    -0.52
     niedersachsen
    -0.52
     daardoor
    -0.52
    Viewed
    -0.52
     obſ
    -0.51
    POSITIVE LOGITS
     tasty
    0.73
     beginnetje
    0.72
     bling
    0.71
     groovy
    0.71
     furry
    0.69
     sweet
    0.69
     shenanigans
    0.68
     festive
    0.68
     frosty
    0.67
     juicy
    0.66
    Act Density 0.353%

    No Known Activations