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

    Neuronpedia

    INDEX
    Explanations

    references to motion or movement

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions, particularly the word "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lank
    -0.67
     Shiite
    -0.63
    :(
    -0.62
     Yemeni
    -0.62
    ļéĨĴ
    -0.60
     Cole
    -0.60
     Beam
    -0.59
     Raiders
    -0.58
     Weekly
    -0.57
     Cortex
    -0.57
    POSITIVE LOGITS
    rew
    0.76
    rogens
    0.73
     congratulate
    0.69
     inspire
    0.69
     groom
    0.67
    yt
    0.65
    /+
    0.64
    romeda
    0.64
     obey
    0.63
     tremb
    0.63
    Act Density 0.230%

    No Known Activations