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

    Neuronpedia

    INDEX
    Explanations

    phrases that express a preference or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sci
    -0.17
    imizer
    -0.16
    sch
    -0.16
    erdale
    -0.16
    uring
    -0.15
    sb
    -0.15
    system
    -0.15
    ald
    -0.15
    sw
    -0.15
    san
    -0.15
    POSITIVE LOGITS
    ìĦľëĬĶ
    0.18
     than
    0.16
    ìĦľ
    0.16
    icher
    0.15
    ÙĨÚ¯ÛĮ
    0.15
    -sex
    0.15
    much
    0.15
    -than
    0.15
    rière
    0.14
    ODE
    0.14
    Act Density 0.018%

    No Known Activations