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

    Neuronpedia

    INDEX
    Explanations

    the word "carry" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dumont
    -0.84
     Tabor
    -0.79
     tulips
    -0.75
     Neust
    -0.73
     grader
    -0.72
     Zeugen
    -0.72
     Conley
    -0.71
     Sodom
    -0.71
     Worms
    -0.71
     tombs
    -0.70
    POSITIVE LOGITS
     carry
    2.52
     carried
    2.41
     Carry
    2.38
     carries
    2.33
    carry
    2.33
     CARRY
    2.27
     carrying
    2.22
    Carry
    2.15
     Carrying
    2.07
    carried
    2.06
    Act Density 0.063%

    No Known Activations