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

    Neuronpedia

    INDEX
    Explanations

    references to safety and decision-making in traffic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.89
    \{\\
    -0.83
     незавершена
    -0.76
     houſe
    -0.75
    numerusform
    -0.74
     }}"></
    -0.74
    "]];
    -0.73
    MemoryWarning
    -0.72
     AssemblyVersion
    -0.71
    });
    -0.70
    POSITIVE LOGITS
     [''
    0.49
     columnist
    0.46
    smtp
    0.45
    Editor
    0.45
     my
    0.44
     column
    0.44
    〈
    0.44
    Composable
    0.44
     readers
    0.43
     Readers
    0.43
    Act Density 0.178%

    No Known Activations