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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ilde
    -0.17
    erb
    -0.15
    ovan
    -0.15
     dro
    -0.15
    еÑĨ
    -0.15
    edy
    -0.14
    hammer
    -0.14
    775
    -0.14
    hatt
    -0.14
    itzer
    -0.14
    POSITIVE LOGITS
    dispose
    0.16
    otel
    0.15
    ìłģìĿ¸
    0.15
    Ø©
    0.14
    ãĥ¥
    0.14
    otle
    0.14
    ormsg
    0.14
    elf
    0.14
    Traits
    0.14
    -owned
    0.13
    Act Density 0.022%

    No Known Activations