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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and the word "that" in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.94
    رشف
    -0.90
    Демографія
    -0.83
    Vidite
    -0.82
     pinulongan
    -0.81
     Wikimedijinoj
    -0.79
     doubtnut
    -0.78
     contextLoads
    -0.78
     }</
    -0.78
    SBATCH
    -0.76
    POSITIVE LOGITS
    .
    0.66
    ,
    0.65
     —
    0.54
     chances
    0.53
    ?
    0.52
     at
    0.50
    ctrica
    0.50
    ;
    0.49
    </i>
    0.48
    ↵↵↵
    0.48
    Act Density 0.025%

    No Known Activations