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

    Neuronpedia

    INDEX
    Explanations

    phrases related to gatherings or events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of large groups of people and social gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reversible
    -0.73
     thesis
    -0.66
     overboard
    -0.66
     drawback
    -0.66
     Chimera
    -0.64
     ambiguity
    -0.60
     torped
    -0.60
     wheels
    -0.60
     withdrawal
    -0.60
     undercut
    -0.60
    POSITIVE LOGITS
     Including
    0.81
    hovah
    0.80
    living
    0.76
     Leban
    0.72
     sidx
    0.72
     Libraries
    0.70
    stand
    0.68
    chat
    0.68
    particularly
    0.68
    internet
    0.68
    Act Density 0.692%

    No Known Activations