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

    Neuronpedia

    INDEX
    Explanations

    verbs that imply action or involvement in certain activities

    oai_token-act-pair · gpt-3.5-turbo

    active verbs related to actions taken by organizations, individuals, or communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sac
    -0.66
     grouping
    -0.62
     Kinnikuman
    -0.60
     assumes
    -0.59
    zip
    -0.59
     Mes
    -0.57
    dt
    -0.57
    ijk
    -0.56
     ending
    -0.56
     preceding
    -0.56
    POSITIVE LOGITS
     Canaver
    0.77
    ADRA
    0.75
    Pixel
    0.69
    igated
    0.68
    urated
    0.68
    Edge
    0.68
    edge
    0.67
    hani
    0.67
    RAG
    0.67
    GGGGGGGG
    0.66
    Act Density 0.364%

    No Known Activations