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

    Neuronpedia

    INDEX
    Explanations

    references to distance and time intervals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    distance or separation

    np_acts-logits-general · gemini-2.0-flash

    distance or separation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     >=",
    -0.64
    )}_
    -0.53
    ноза
    -0.51
     sī
    -0.51
    ]--;
    -0.49
    >");
    -0.48
     }}>
    -0.48
    hdashline
    -0.48
    )*/
    -0.47
    /');
    -0.47
    POSITIVE LOGITS
     away
    1.20
     separation
    0.86
     separates
    0.86
     separated
    0.84
     separating
    0.83
    away
    0.80
    separated
    0.79
     AWAY
    0.78
     Away
    0.77
     difference
    0.77
    Act Density 0.139%

    No Known Activations