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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     كومونز
    -0.62
    WriteBarrier
    -0.58
    AsUp
    -0.56
    RegistryLite
    -0.55
     ddelweddau
    -0.55
    énieurs
    -0.53
    Kjelder
    -0.53
     MonoBehaviour
    -0.51
    sterone
    -0.51
     asyncio
    -0.50
    POSITIVE LOGITS
     pleaſure
    0.66
     myſelf
    0.61
    enderror
    0.57
     purpoſe
    0.57
     specchio
    0.56
     enco
    0.56
     stabilisation
    0.56
    makeConstraints
    0.55
     pleaf
    0.54
     ſtand
    0.54
    Act Density 0.020%

    No Known Activations