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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     fullPath
    -0.08
    attr
    -0.07
     pirate
    -0.07
    阄
    -0.07
     envisioned
    -0.07
     vscode
    -0.07
    .readInt
    -0.07
     newText
    -0.07
     describes
    -0.07
    /plain
    -0.07
    POSITIVE LOGITS
     erv
    0.08
    හ
    0.07
    טות
    0.07
     KNOW
    0.07
    킨
    0.07
     Labels
    0.07
     HERO
    0.07
    బ
    0.07
    キン
    0.07
    BERT
    0.07
    Act Density 0.000%

    No Known Activations