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

    Neuronpedia

    INDEX
    Explanations

    recommendations or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of recommendation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kered
    -0.74
     Bom
    -0.66
    aque
    -0.62
     Ern
    -0.62
    amorph
    -0.62
    woods
    -0.60
    catentry
    -0.60
    von
    -0.60
     POW
    -0.60
     attendant
    -0.59
    POSITIVE LOGITS
    ENDED
    0.81
    avorite
    0.79
    ournals
    0.78
    Recommend
    0.75
     recommending
    0.70
    recomm
    0.70
    Pad
    0.69
    FontSize
    0.68
    Recommended
    0.68
    Ļ½
    0.67
    Act Density 0.032%

    No Known Activations