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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize the need for improvement or enhanced understanding

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     prestasi
    -0.88
     performance
    -0.84
     Performance
    -0.83
     PERFORMANCE
    -0.82
    Результа
    -0.82
    Performance
    -0.77
    istungen
    -0.76
    performance
    -0.75
    Œuvres
    -0.73
    ítmény
    -0.73
    POSITIVE LOGITS
    ely
    0.80
    ing
    0.73
    ed
    0.71
    ting
    0.68
     Hathaway
    0.66
    izing
    0.65
    )^{-
    0.65
    ▬▬▬▬
    0.63
    ying
    0.62
    o
    0.61
    Act Density 0.022%

    No Known Activations