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

    Neuronpedia

    INDEX
    Explanations

    recommendations given in text

    oai_token-act-pair · gpt-3.5-turbo

    recommendations and endorsements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tal
    -0.77
    cod
    -0.74
    san
    -0.71
    Sus
    -0.71
     Alic
    -0.68
    sen
    -0.67
    vous
    -0.67
    von
    -0.66
     Ern
    -0.65
    kered
    -0.65
    POSITIVE LOGITS
     recommending
    1.10
     recommend
    1.08
    recomm
    1.03
     recommends
    1.03
     recommendations
    0.94
    Recommend
    0.94
     recommended
    0.93
     recommendation
    0.90
    avorite
    0.88
     livest
    0.88
    Act Density 0.014%

    No Known Activations