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

    Neuronpedia

    INDEX
    Explanations

    phrases related to participation or involvement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating participation in various activities or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulence
    -0.68
     clocks
    -0.67
    oxin
    -0.66
    wyn
    -0.63
     ambig
    -0.63
    uncle
    -0.61
    aeus
    -0.60
     latch
    -0.60
    mother
    -0.59
     inexper
    -0.59
    POSITIVE LOGITS
     conversation
    0.83
     discussions
    0.80
     hostilities
    0.78
     voluntary
    0.77
     conversations
    0.76
    ordinate
    0.75
     accordance
    0.71
     activities
    0.69
     negotiations
    0.69
     Scouting
    0.68
    Act Density 0.085%

    No Known Activations