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

    terms related to pathways or routes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ished
    -0.84
    onom
    -0.74
    ishing
    -0.72
    ores
    -0.72
    olls
    -0.71
    ucks
    -0.69
    rikes
    -0.69
    rongh
    -0.67
    itarian
    -0.65
    ishes
    -0.64
    POSITIVE LOGITS
    xual
    1.00
     pathways
    0.98
     pathway
    0.97
    ways
    0.96
    WAYS
    0.94
     paths
    0.83
    iferation
    0.81
    utics
    0.75
    anwhile
    0.74
    ="#
    0.74
    Act Density 0.025%

    No Known Activations