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

    Neuronpedia

    INDEX
    Explanations

    comparative and superlative adjectives related to measurement or evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Joachim
    -0.55
     Field
    -0.52
     Cyclo
    -0.52
     Epistle
    -0.52
    Field
    -0.52
     Candle
    -0.52
    AdapterView
    -0.51
    anilla
    -0.51
     array
    -0.51
     field
    -0.50
    POSITIVE LOGITS
     betweenstory
    0.64
    faster
    0.51
    higher
    0.51
    DotNetBar
    0.51
     leſs
    0.49
     fairer
    0.49
    seventh
    0.48
    larger
    0.48
    smaller
    0.47
    further
    0.46
    Act Density 0.207%

    No Known Activations