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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the name "Alex" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èħ
    -0.19
    taj
    -0.17
    alamat
    -0.17
    clas
    -0.15
    loub
    -0.15
    reste
    -0.15
    icky
    -0.14
    geh
    -0.14
    HING
    -0.14
    ông
    -0.14
    POSITIVE LOGITS
    ei
    0.36
    andra
    0.32
    ander
    0.30
    andr
    0.27
    ey
    0.26
    andre
    0.25
    andro
    0.23
    ender
    0.21
    stras
    0.21
    ej
    0.20
    Act Density 0.006%

    No Known Activations