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

    Neuronpedia

    INDEX
    Explanations

    verbs and adjectives related to personal behavior

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     logis
    -0.65
     starte
    -0.62
     buk
    -0.61
     tages
    -0.60
     puc
    -0.60
     opio
    -0.59
     Lider
    -0.59
     stopp
    -0.58
     mola
    -0.58
     dises
    -0.58
    POSITIVE LOGITS
    Tend
    1.09
     tend
    1.03
     Tend
    0.98
     tended
    0.92
     TEND
    0.91
     tends
    0.86
     tending
    0.86
    tend
    0.81
     tendance
    0.76
     tendency
    0.74
    Act Density 0.052%

    No Known Activations