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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various activities and events happening at a particular place

    oai_token-act-pair · gpt-3.5-turbo

    terms related to events, meetings, or gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himself
    -0.94
     Himself
    -0.83
     herself
    -0.79
    tein
    -0.78
     oneself
    -0.77
     themselves
    -0.74
     Canaver
    -0.71
    opped
    -0.70
     Adolf
    -0.67
    auri
    -0.65
    POSITIVE LOGITS
     selves
    1.02
     partners
    0.93
     counterparts
    0.83
     asses
    0.83
     ancestors
    0.83
     colleague
    0.81
     brethren
    0.81
     partner
    0.79
     endeavors
    0.76
     overl
    0.75
    Act Density 0.379%

    No Known Activations