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

    Neuronpedia

    INDEX
    Explanations

    comparative or contrasting statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imei
    -0.17
    USTER
    -0.16
    iyim
    -0.16
    ifton
    -0.15
    andes
    -0.15
    locker
    -0.15
    iyah
    -0.14
    rung
    -0.14
     McCart
    -0.14
    iê
    -0.14
    POSITIVE LOGITS
    867
    0.16
    haus
    0.16
    borg
    0.15
    enthal
    0.14
     ked
    0.14
     Toy
    0.14
    bast
    0.14
    alem
    0.14
    гÑĥ
    0.14
    Toy
    0.14
    Act Density 0.000%

    No Known Activations