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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating evaluation or judgment

    oai_token-act-pair · gpt-3.5-turbo

    phrases centered around assertions, claims, or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lawy
    -0.76
     flyers
    -0.75
     resur
    -0.70
     flo
    -0.68
     bil
    -0.66
     clipboard
    -0.66
     HUD
    -0.65
     mobs
    -0.65
     chest
    -0.64
     lymph
    -0.62
    POSITIVE LOGITS
    ception
    0.80
    paralle
    0.75
    answer
    0.75
    udos
    0.74
    agine
    0.74
    ãĤ¦ãĤ¹
    0.72
    thinkable
    0.71
     Attribution
    0.68
     Prediction
    0.68
    trace
    0.68
    Act Density 0.247%

    No Known Activations