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

    Neuronpedia

    INDEX
    Explanations

    the word "su" and its variations, indicating a focus on suffixes or specific word endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lops
    -0.18
    581
    -0.18
    asters
    -0.17
    uchs
    -0.17
    aft
    -0.16
    egov
    -0.15
    yne
    -0.14
    oust
    -0.14
    bal
    -0.14
    ASTER
    -0.14
    POSITIVE LOGITS
    nde
    0.22
    arez
    0.21
    nda
    0.21
    icide
    0.21
    ave
    0.20
    cession
    0.19
    éĨĴ
    0.19
    ceeded
    0.19
    pected
    0.19
    icides
    0.19
    Act Density 0.006%

    No Known Activations