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

    Neuronpedia

    INDEX
    Explanations

    expressions of intense emotions and conflicts, particularly related to love and physical confrontation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascus
    -0.81
     favourable
    -0.78
     compr
    -0.78
     advoc
    -0.77
    eatured
    -0.77
     encount
    -0.77
     carbohyd
    -0.76
     brid
    -0.76
     necess
    -0.74
    perty
    -0.74
    POSITIVE LOGITS
     Literally
    1.43
     Especially
    1.41
     And
    1.37
     Because
    1.31
     But
    1.30
     Maybe
    1.29
     Anyway
    1.28
     Seriously
    1.27
     Except
    1.26
     Lots
    1.26
    Act Density 1.560%

    No Known Activations