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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "in [number]"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NOW
    -0.73
    ĪĴ
    -0.68
    elson
    -0.67
    ihad
    -0.65
    Guide
    -0.65
     Donation
    -0.64
    ignty
    -0.62
    IJ
    -0.61
    elf
    -0.60
    CRIPTION
    -0.60
    POSITIVE LOGITS
     infancy
    1.08
     situ
    1.07
    escap
    0.98
    animate
    0.96
    operative
    0.94
     limbo
    0.94
    accessible
    0.92
    ching
    0.89
    ked
    0.89
    active
    0.87
    Act Density 0.051%

    No Known Activations