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

    Neuronpedia

    INDEX
    Explanations

    expressions related to the action of stopping

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.88
    hydrates
    -0.83
    disposing
    -0.77
    données
    -0.77
    ”)
    -0.75
    }`)
    -0.75
    הערות
    -0.72
    }$​
    -0.72
     ")");
    -0.71
    mtext
    -0.70
    POSITIVE LOGITS
     stops
    2.01
     stop
    1.93
     Stop
    1.93
     STOP
    1.93
     Stops
    1.93
    Stop
    1.83
    stop
    1.82
    stops
    1.81
    STOP
    1.77
    Stops
    1.69
    Act Density 0.062%

    No Known Activations