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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing preference for undesirable alternatives over social norms or conventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kív
    -0.45
    SizeF
    -0.44
     למע
    -0.41
     including
    -0.40
    toContain
    -0.40
    kres
    -0.39
     sauvages
    -0.39
     foglal
    -0.38
     Hals
    -0.38
    addCriterion
    -0.38
    POSITIVE LOGITS
     }}"></
    0.83
    VersionUID
    0.82
     lenker
    0.80
     متعلقه
    0.77
     than
    0.75
     ujednoznacz
    0.74
    sidemargin
    0.71
     createContext
    0.70
     THAN
    0.69
    Hozzáférés
    0.69
    Act Density 0.159%

    No Known Activations