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

    Neuronpedia

    INDEX
    Explanations

    names of people or companies that have made decisions or taken actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant actions or decisions made by groups or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eye
    -0.68
    akra
    -0.65
    PIN
    -0.60
    Streamer
    -0.59
    uggle
    -0.58
     MH
    -0.58
    icy
    -0.58
    hess
    -0.57
    uddin
    -0.57
    igraph
    -0.56
    POSITIVE LOGITS
    enegger
    0.90
    anwhile
    0.90
     notwithstanding
    0.86
     unsurprisingly
    0.75
     preferably
    0.69
     boycot
    0.63
    thirds
    0.63
     economists
    0.62
    reditary
    0.60
     incorpor
    0.60
    Act Density 3.666%

    No Known Activations