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

    Neuronpedia

    INDEX
    Explanations

    references to bots, particularly in a technical or programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     default
    -0.47
     concept
    -0.46
     Logan
    -0.45
     book
    -0.45
     forward
    -0.43
     Forward
    -0.43
     theory
    -0.42
     Boek
    -0.42
     kans
    -0.42
     question
    -0.42
    POSITIVE LOGITS
    Bot
    0.78
    bot
    0.71
     betweenstory
    0.70
    BOT
    0.68
    SBATCH
    0.66
    WebMethod
    0.66
     Bot
    0.65
     ſind
    0.63
    setVerticalGroup
    0.60
     varieties
    0.60
    Act Density 0.199%

    No Known Activations