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

    Neuronpedia

    INDEX
    Explanations

    code that includes blocks and structures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     poveznice
    -0.55
    velse
    -0.52
     Weltkrieg
    -0.50
     bearer
    -0.49
     viciss
    -0.49
     gani
    -0.48
    AsUp
    -0.47
    خصة
    -0.47
     cât
    -0.47
    ècie
    -0.46
    POSITIVE LOGITS
    setVerticalGroup
    0.69
    ')],
    0.68
    ]";
    0.65
    **/
    0.64
     propOrder
    0.63
    ')";
    0.62
    "):
    0.61
    }';
    0.61
    ]`
    0.61
    aarrggbb
    0.61
    Act Density 0.010%

    No Known Activations