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

    Neuronpedia

    INDEX
    Explanations

    phrases related to importance or observation

    oai_token-act-pair · gpt-3.5-turbo

    important concepts and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     workflow
    -0.74
     sabot
    -0.72
     intimid
    -0.68
     stunts
    -0.65
    doors
    -0.63
     stunt
    -0.62
     overboard
    -0.61
     practices
    -0.60
     bottleneck
    -0.60
     coerc
    -0.60
    POSITIVE LOGITS
     remem
    0.96
     recall
    0.93
    remember
    0.92
     recol
    0.91
     infer
    0.90
     recollection
    0.88
     Recall
    0.86
     conjecture
    0.86
     conject
    0.85
     historians
    0.84
    Act Density 1.122%

    No Known Activations