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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate quantities and statistical measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     meste
    -0.70
     '*')
    -0.64
     saken
    -0.63
     récompenses
    -0.61
     تانيه
    -0.60
     الحره
    -0.60
     campeones
    -0.57
     dachte
    -0.57
     degradability
    -0.57
    Trails
    -0.56
    POSITIVE LOGITS
     numberOf
    1.13
     number
    1.11
    numberOf
    1.05
     fewer
    1.00
    NumberOf
    0.93
    DockStyle
    0.92
     Number
    0.91
    numbered
    0.90
    WithMany
    0.88
    antMatchers
    0.88
    Act Density 0.235%

    No Known Activations