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

    Neuronpedia

    INDEX
    Explanations

    prefixes indicating negation or reversal

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Pre
    -0.71
    i
    -0.68
    Ex
    -0.68
    Com
    -0.66
    pre
    -0.63
    anti
    -0.63
     anti
    -0.63
    ex
    -0.62
    Post
    -0.62
    Cor
    -0.61
    POSITIVE LOGITS
    ItemBackground
    1.20
     Италијани
    1.05
    Fordítás
    1.01
     ivelany
    0.99
    ✨:
    0.98
    ]")]
    0.96
    }}/>
    0.94
    Fitment
    0.94
     Мексичка
    0.93
    PreferredItem
    0.92
    Act Density 0.096%

    No Known Activations