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

    Neuronpedia

    INDEX
    Explanations

    phrases related to pathways or routes

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of pathways

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orian
    -0.78
    uster
    -0.70
    onom
    -0.69
    wig
    -0.66
     Aires
    -0.65
     Lomb
    -0.64
     fluffy
    -0.64
    olls
    -0.64
     gritty
    -0.63
     Gael
    -0.63
    POSITIVE LOGITS
     pathway
    1.17
     pathways
    1.17
    xual
    0.98
    ways
    0.86
    utics
    0.85
     cascade
    0.85
    WAYS
    0.84
     paths
    0.84
     casc
    0.81
     inhibitors
    0.81
    Act Density 0.011%

    No Known Activations