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

    Neuronpedia

    INDEX
    Explanations

    references to personal actions and experiences of returning or transitioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahn
    -0.15
    ɵ
    -0.15
    ovan
    -0.15
    ronym
    -0.14
    .AnchorStyles
    -0.14
    reet
    -0.14
    unks
    -0.14
    ochen
    -0.14
    鬼
    -0.14
    ÚĺÛĮ
    -0.13
    POSITIVE LOGITS
     return
    0.43
     back
    0.42
     returned
    0.40
     returning
    0.39
    return
    0.37
     terug
    0.36
     returns
    0.36
     Return
    0.36
    è¿ĶåĽŀ
    0.36
     RETURN
    0.35
    Act Density 0.133%

    No Known Activations