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

    Neuronpedia

    INDEX
    Explanations

    descriptions of parts of things or larger quantities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to injuries and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     presided
    -0.63
     recess
    -0.61
    ente
    -0.60
    oris
    -0.58
     industrialized
    -0.56
    meet
    -0.55
     adaptation
    -0.54
     supervision
    -0.53
    opt
    -0.53
     appoint
    -0.53
    POSITIVE LOGITS
    abytes
    0.81
     stains
    0.73
     fragments
    0.73
    artifacts
    0.71
    âĵĺ
    0.70
     scratches
    0.68
     souven
    0.68
    umbnails
    0.67
    estones
    0.67
     artifacts
    0.66
    Act Density 1.028%

    No Known Activations