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

    Neuronpedia

    INDEX
    Explanations

    instances where something is accurately identified or sensed

    oai_token-act-pair · gpt-3.5-turbo

    terms related to detection and recognition processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ylum
    -0.72
    cloth
    -0.70
    cake
    -0.69
    usp
    -0.69
    union
    -0.68
    apters
    -0.67
    rette
    -0.67
    lli
    -0.64
    undy
    -0.64
    udeb
    -0.64
    POSITIVE LOGITS
     accuracy
    0.88
     detect
    0.86
     detecting
    0.85
     predictive
    0.85
    alys
    0.81
     accurately
    0.80
     neural
    0.80
     diagn
    0.79
     algorithms
    0.78
     accurate
    0.77
    Act Density 0.432%

    No Known Activations