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

    Neuronpedia

    INDEX
    Explanations

    participation in groups or events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    glass
    -0.75
     clocks
    -0.68
    arily
    -0.67
    aeus
    -0.66
    ulence
    -0.64
    oxin
    -0.63
    ulum
    -0.63
     lodged
    -0.63
    anted
    -0.62
    types
    -0.61
    POSITIVE LOGITS
     fray
    0.93
     hostilities
    0.91
     discussions
    0.83
     conversation
    0.79
     debates
    0.74
    ADRA
    0.72
    ordinate
    0.71
     conversations
    0.70
    clus
    0.69
     Unch
    0.68
    Act Density 1.478%

    No Known Activations