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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical references and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lance
    -0.69
     Refer
    -0.68
    JO
    -0.67
    AAF
    -0.67
    MSN
    -0.65
     Signs
    -0.64
     TOUR
    -0.64
    conservancy
    -0.63
     PID
    -0.63
     Pione
    -0.61
    POSITIVE LOGITS
    ths
    1.12
    teenth
    1.10
    ieth
    0.96
    enged
    0.87
    eenth
    0.79
    tarian
    0.75
    ighty
    0.75
    teen
    0.74
    undred
    0.74
     punch
    0.73
    Act Density 0.024%

    No Known Activations