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

    Neuronpedia

    INDEX
    Explanations

    bracketed or enclosed symbols in mathematical or structured text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cerned
    -0.58
    IBU
    -0.51
     hardwoods
    -0.50
     удо
    -0.49
     Darth
    -0.47
     glatt
    -0.47
     divertimento
    -0.46
     musique
    -0.45
     Musica
    -0.45
    niosek
    -0.45
    POSITIVE LOGITS
    
    0.85
    tagHelperRunner
    0.82
    enumi
    0.81
    ImageContext
    0.80
     يتيمه
    0.77
    RectangleBorder
    0.76
    Geplaatst
    0.74
     <<<<<<<<<<<<<<
    0.70
    Hochspringen
    0.68
    GenerationType
    0.68
    Act Density 0.296%

    No Known Activations