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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making adjustments or changes, particularly in the context of following and modifying a recipe or instructions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    BeginContext
    -0.54
    älde
    -0.50
     gyhoeddwyd
    -0.47
    essero
    -0.47
     magique
    -0.47
     scolaires
    -0.45
    Unspecified
    -0.43
     vagues
    -0.43
     Dyck
    -0.42
     كمان
    -0.41
    POSITIVE LOGITS
    setAccessible
    0.78
     ویکی‌پدیا
    0.68
    UserScript
    0.61
     extra
    0.59
     customise
    0.59
     unofficial
    0.58
     ujednoznacz
    0.58
     nî
    0.58
     customised
    0.57
    ̀
    0.56
    Act Density 0.324%

    No Known Activations