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

    Neuronpedia

    INDEX
    Explanations

    questions within a text

    oai_token-act-pair · gpt-3.5-turbo

    questions throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     carbohyd
    -0.81
     affili
    -0.77
     referen
    -0.76
     transition
    -0.76
     exting
    -0.72
     corrid
    -0.71
     bonded
    -0.71
     slightest
    -0.70
     merging
    -0.70
    ikuman
    -0.69
    POSITIVE LOGITS
     Well
    1.78
     Probably
    1.44
     Firstly
    1.37
     Plenty
    1.32
     Quite
    1.32
     Apparently
    1.32
     Surprisingly
    1.31
     Surely
    1.30
    Well
    1.29
     Simple
    1.29
    Act Density 0.116%

    No Known Activations